Professor Hany Farid

photo credit: Christopher Michel
BIO
I am a Professor at the University of California, Berkeley with a joint appointment in Electrical Engineering & Computer Sciences and the School of Information. I am also the co-founder and Chief Science Officer at GetReal Labs. My research focuses on digital forensics, forensic science, misinformation, image analysis, and human perception. I received my undergraduate degree in Computer Science and Applied Mathematics from the University of Rochester in 1989, my M.S. in Computer Science from SUNY Albany in 1992, and my Ph.D. in Computer Science from the University of Pennsylvania in 1997. Following a two-year post-doctoral fellowship in Brain and Cognitive Sciences at MIT, I joined the faculty at Dartmouth College in 1999 where I remained until 2019. I am the recipient of an Alfred P. Sloan Fellowship, a John Simon Guggenheim Fellowship, and am a Fellow of the National Academy of Inventors.
TUTORIALS
  1. Learn Computer Vision [video tutorials]
  2. Learn to Code in Python [video tutorials]
  3. Physics-Based Photo Forensics [video tutorials]
  4. H. Farid. Fake Photos, MIT Press Essential Knowledge series, 2019. [Publisher] [Amazon]
  5. H. Farid. Photo Forensics. MIT Press, 2016. [Publisher] [Amazon] [Table of Contents, Preface, Introduction]
  6. Digital Image Forensics: lecture notes, exercises, and matlab code for a survey course in digital image and video forensics. [tutorial]
  7. Fundamentals of Image Processing: learn about the fundamentals of signal and image processing within a unifying mathematical framework. [tutorial]
  8. How to Give a Good Talk. [tutorial]
  9. How to Write a Good Grant. [tutorial]
  10. How to Write a Good Review. [tutorial]
TALKS
  1. A Break Down of Political Deepfakes, 2024 [watch]
  2. Combatting Deep Fakes, IEEE Biometrics Council, 2022 [watch]
  3. Detecting Disinformation and Deep Fakes, Science @ Cal, 2022 [watch]
  4. Assessing the Reliability of Clothing Based Forensic Identification, DiMACS Workshop on Computer Science and Law, 2020. [watch]
  5. Creating, Weaponizing, and Detecting Deep Fakes, Spark + AI Summit, 2020 [watch]
  6. The Danger of Predictive Algorithms in Criminal Justice, TEDx AmoskeagMillyard, 2018 [watch]
  7. Digital Forensics: From Social Media to Social Impact, National Academy of Inventors, 2017 [watch]
CODE
  1. CGI or Photo? [download]
  2. Clutter: quantify the amount of clutter in an image [download]
  3. Derivative Filters [download]
  4. Forensic Reconstruction of Severeley Degraded License Plates [github]
  5. Fractional Differentiation [download]
  6. Fractional Fourier Transform [download]
  7. Gamma Correction: blind removal of gamma correction [download]
  8. ICA: separating reflections [download]
  9. Phototop: surface topography from unconstrained photos [download]
  10. Q: an interface to Matlab for manipulating and analyzing digital images [download]
  11. Qr: image registration [download]
  12. Q5: probabilistic disease classification mass spectrometry [download]
  13. RAMBiNo: A Toolbox for the Radial and Angular Marginalization of Bivariate Normal Distributions [github]
  14. SPHARM: 3-D spherical harmonic analyses on triangular mesh surfaces [download]
  15. Steerable wedge filters [download]
  16. Steganalysis [download]
  17. Wild-ID: pattern extraction and matching for use in photographic mark-recapture studies [download]
BLOG
    A six-part blog series on the history of photo manipulation and photo forensics written for the Content Authenticity Initiative
    1. From the darkroom to generative AI [read]
    2. How realistic are AI-generated faces? [read]
    3. Photo forensics for AI-generated faces [read]
    4. Photo forensics from lighting environments [read]
    5. Photo forensics from lighting shadows and reflections [read]
    6. Passive versus active photo forensics in the age of AI and social media [read]

    A monthly blog series on current trends in Generative AI written for the Content Authenticity Initiative
    1. January 2024 | This Month in Generative AI: Frauds and Scams [read]
    2. February 2024 | This Month in Generative AI: Election Season [read]
    3. March 2024 | This Month in Generative AI: Text-to-Movie [read]
    4. April 2024 | This Month in Generative AI: Deepfakes, Real Consequences [read]
    5. May 2024 | This Month in Generative AI: Technology is no Subsitute for Common Sense [read]
    6. June 2024 | This Month in Generative AI: Moving Through the Uncanny Valley [read]
    7. July 2024 | This Month in Generative AI: Moving Through the Uncanny Valley (Pt. 2 of 2) [read]
    8. August 2024 | This Month in Generative AI: Forensics Weaponized [read]
    9. September 2024 | This Month in Generative AI: Taylor Swift's AI Fears are Not Unfounded [read]
    10. October 2024 | This Month in Generative AI: California Legislatures Have Been Busy [read]
OP-EDS
  1. Why the Fake Biden Videos Flooding Social Media are More Insidious than they Appear, MSNBC, 6.18.24 [read]
  2. A Forensics Expert on Princess Kate's Photo, Time Magazine, 3.12.24 [read]
  3. Why are there so many images of child abuse stored on iCloud? Because Apple allows it. San Francisco Chronicle, 10.8.23 [read]
  4. Yes, We Should Regulate AI-Generated Politcal Ads -- But Don't Stop There, The Hill, 8.14.23 [read]
  5. Watermarking ChatGPT, DALL-E and Other Generative AIs Could Help Protect Against Fraud and Misinformation, The Conversation, 3.27.23 [read]
  6. The Case for Regulating Platform Design, Wired 3.13.23 [read]
  7. Text-to-Image AI: Powerful, Easy-to-Use Technology for Making Art - and Fakes, The Conversation, 12.5.22 [read]
  8. This Is the Worst Time for Donald Trump to Return to Twitter, Slate, 11.20.22 [read]
  9. Don't Let Fearmongering Derail a New Law That Has Real Teeth to Protect Kids' Privacy, Gizmodo, 9.8.22 [read]
  10. Should We Celebrate or Condemn Apple's New Child Protection Measures?, Newsweek, 8.13.21 [read]
  11. The Case for Trump's Permanent Ban From Social Media, Slate, 2.5.21 [read]
  12. We Have the Technology to Fight Manipulated Images and Videos. It's Time to Use it, Fast Company, 11.18.20 [read]
  13. Congress Needs to Make Silicon Valley EARN IT, Wired, 7.5.20 [read]
  14. Google Is Not Cracking Down on the Most Dangerous Drug in America, Newsweek, 6.11.20 [read]
  15. Facebook's Encryption Makes it Harder to Detect Child Abuse, Wired, 10.25.19 [read]
  16. Deepfakes Give New Meaning to the Concept of 'fake news,' and They're Here to Stay, Fox News, 6.18.19 [read]
  17. Facebook's Plan for End-to-End Encryption Sacrifices a Lot of Security for Just a Little Bit of Privacy, Fox News, 6.16.19 [read]
  18. Tech Companies Must Act to Stop Horrific Exploitation of their Platforms, The Hill, 4.17.19 [read]
  19. YouTube's Paedophile Problem is Only a Small Part of the Internet's Issue with Child Sexual Abuse. The Conversation, 3.5.19. [read]
  20. Facebook, YouTube and Social Media are Failing Society: Pull their ads until they change, USA Today, 3.4.19, [read]
  21. Don't be Fooled by Fake Images and Videos Online. The Conversation, 2.20.19 [read]
  22. Reining in a Morally Bankrupt Technology Sector, Our World, 1.21.19 [read]
  23. Recruiting Terrorists: We're losing the fight against online extremism - here's why, The Hill, 8.2.18 [read]
  24. Verifying BigTech Promises, EUReporter, 5.11.18 [read]
  25. Are Universities Fueling Silicon Valley Crisis?, Union Leader, 2.9.18 [read]
  26. Technology Sector Should not be Shielding Sex Traffickers Online, The Hill, 9.19.17 [read]
  27. Internet Companies Right to Close Neo-Nazi Sites, but Terror Still too Easy to Find, The Hill, 9.11.17 [read]
IN THE NEWS (recent)
      DIGITAL FORENSICS
  1. Deepfakes, AI and the Battle for Democracy. Zeteo, 11.9.24 [watch]
  2. AI Audio Deepfakes Are Quickly Outpacing Detection. Scientific American, 1.26.24 [read]
  3. AI Images Detectors Are Being Used to Discredit the Real Horrors of War. 404 Media, 10.13.23 [read]
  4. How Real is the Threat of AI Deepfakes in the 2024 Election? NPR's Weekend Edition, 7.30.23 [listen]
  5. Reality Wars: Deepfakes and National Security, NPR, On Point, 6.7.23 [listen]
  6. Deepfakes Are Getting Better, KQED, The Forum, 10.16.23 [listen]
  7. CNN reporter calls his parents using AI voice. Watch what happens next, CNN, 3.8.23 [watch]
  8. AI Spots Deepfake Videos of Ukrainian President Volodymyr Zelenskyy, New Scientist, 12.7.22 [read]
  9. DALL-E, Deepfakes and the New Frontier of Online Misinformation, KQED, The Forum, 8.26.22 [listen]
  10. As Tech Evolves, Deepfakes Will Become Even Harder to Spot, NPR, Weekend Edition Sunday 7.3.22 [listen]
  11. Humans Find AI-Generated Faces More Trustworthy Than the Real Thing, Scientific American, 2.14.22 [read]
  12. Why People Think this Photo of JFK's Killer is Fake, VOX Darkroom, 9.2.21 [watch]
  13. Deepfake Videos are Becoming Easier To Make But Dangerously Difficult To Identify, ABC Nightline, 3.19.21 [watch]
  14. Slick Tom Cruise Deepfakes Signal That Near Flawless Forgeries May Be Here, NPR, All Things Considered, 3.11.21 [listen]
  15. Can YouTube Quiet Its Conspiracy Theorists?, New York Times, 3.2.20 [read]

      FORENSIC SCIENCE
  1. Denim, as a Crime-Solving Tool, Has Holes, New York Times, 4.8.20 [read]
  2. A Key FBI Photo Analysis Method Has Serious Flaws, Study Says, ProPublica, 2.25.20 [read]
  3. Do Predictive Algorithms Have A Place In Public Policy?, Science Friday, 1.19.18 [listen]
  4. Can Software Predict Crime? Maybe So, but No Better Than a Human, New York Times, 1.19.18 [read]

      COUNTER EXTREMISM
  1. 'A catastrophic failure': computer scientist Hany Farid on why violent videos circulate on the internet, The Guardian, 5.19.22 [read]
  2. Facebook Challenged to Rein in Extremism, CBS News, 2.12.19 [watch]
  3. YouTube is Still Failing to Take Down Jihadi Propaganda, Daily Mail, 7.24.18 [read]
  4. Detecting and Preventing the Upload of Extreme Content, Bloomberg, 4.4.18 [watch]
  5. Would a Global Cyber Ethics Commission Help 'counter the lies' of the Tech Lobby?, Deutsche Welle, 3.27.18 [read]
  6. Combating Extremism Online, The Open Mind, 3.3.18 [watch]

      PERSONAL PROFILE
  1. The Most Creative People in Business 2018, Fast Company, 5.30.18 [read]
  2. New Hampshire's People of the Year, NH Magazine, 12.1.17 [read]
  3. Fighting Digital Depravity, Enterprise Magazine, Valley News, 2.27.17 [read]
  4. The Digital Detective, San Jose Mercury News, 12.15.08 [read]
  5. Profile: Hany Farid, NOVA, scienceNOW, 6.25.08 [watch]
  6. Mathematical Sleuthing, New Hampshire Magazine, 2.1.05 [read]
  7. Digital Forensics, NHPR Front Porch, 12.14.04 [listen]

      IMDb PROFILE
PODCASTS (recent)
  1. The Trouble with Deepfakes: Liar's Dividend, FT Tech Tonic, 8.22.24 [listen]
  2. AI is a Misinformation Amplifier, The Times' Danny in the Valley, 7.11.24 [listen]
  3. The Threat Of Deepfakes In The 2024 Election, Diane Rehm, 2.1.24 [listen]
  4. Why AI Keeps Getting Better at Making Fake Images, Wall Street Journal's The Future of Everything, 1.19.24 [listen]
  5. Here's Why Actors Are So Worried About AI, Scientific American, 7.26.23 [listen]
  6. With AI, We're Making the Same Mistakes That We Did With Social Media, The Times' Danny in the Valley, 6.8.23 [listen]
  7. Generative AI, Section 230 and Liability: Assessing the Questions, Tech Policy Press, 3.23.23 [listen]
  8. Will Killing Section 230 Kill the Internet?, On With Kara Swisher, 2.23.23 [listen]
  9. Musk's Twitter Takeover and the State of Social Media, The Times' Danny in the Valley, 5.7.22 [listen]
  10. Can Data Science Help Us Combat Disinformation?, Harvard Data Science Review, 9.29.21 [listen]
  11. The Deepfake Detective, Should This Exist, 10.14.20 [listen]
  12. Deepfakes and the Future of Truth, Brave New Planet, 10.12.20 [listen, iTunes]
  13. Deep Fakes, Full Fact, 10.5.20 [iTunes, Spotify]
  14. Hany Farid on Deep Fakes, Doctored Photos and Disinformation, Lawfare, 7.23.20 [listen]
  15. Misinformation Apocalypse, Stay Tuned with Preet Bharara, 3.5.20 [listen]
ALUMNI
  1. Shruti Agarwal (Ph.D., 2021) [dissertation]
  2. Tiago Carvalho (visiting Ph.D. student, UNICAMP, Brazil, 2014)
  3. Emma Chiu '19
  4. Valentina Conotter (visiting Ph.D. student, University of Trento, 2011) [dissertation]
  5. Julia Dressel '17 [thesis]
  6. Marc Faddoul (M.S., 2019)
  7. Wei Fan (postdoc, 2018)
  8. Olivia Holmes '15 [thesis]
  9. Daniel Hopkins '10
  10. Kimo Johnson (Ph.D., 2007) [dissertation]
  11. Simran Kaur (UC Berkeley, Haas Scholar, 2021)
  12. Eric Kee (Ph.D., 2013) [dissertation]
  13. Benedikt Lorch (visiting M.S. student, University of Erlangen, 2018)
  14. Siwei Lyu (Ph.D., 2005) [dissertation]
  15. Brandon Mader '17
  16. Hafiz Malik (visiting professor, 2009)
  17. David Martin '00
  18. Sophie Nightingale (postdoc, 2020)
  19. Joseph Pechter '04
  20. William Pechter '04
  21. Senthil Periaswamy (Ph.D., 2003) [dissertation]
  22. Coralie Phanord '16
  23. Andrew Pierce '02
  24. Alin Popescu (Ph.D., 2005) [dissertation]
  25. Jethro Rothe-Kushel '03
  26. Vibhor Sehgal (M.S., 2021)
  27. Katherine Sherwin '01
  28. Priyanka Singh (postdoc, 2019)
  29. Hai Sun (M.D./Ph.D., 2004) [dissertation]
  30. Elliott Waissbluth (M.S., 2022)
  31. Josh Wang '15
  32. Weihong Wang (Ph.D., 2009) [dissertation]
  33. Jeff Woodward (Programmer)
  34. Angela Zhu '17
JOIN US
  1. Prospective Ph.D. students
    • I will not be accepting new Ph.D. students in Fall 2024 or 2025.
    • I hold a joint appointment in Electrical Engineering & Computer Sciences and the School of Information. I encourage you to look at the program requirements to decide which is the best fit for you (you may only apply to one of these programs). Generally speaking, EECS will be a better fit for those with a strong computational and mathematical background, and the I School will be a better fit for those with more of an interdisciplinary background. I do not directly admit students into the program, rather Ph.D. graduate admissions are handled by a department/school-level committee. This committee considers the standard criteria of prior academic performance, prior research experience, letters of recommendation, statement of purpose, and community and diversity.
    • When applying please pay careful attention to your research statement. It should express a clear research question or project, and articulate why your background sets you up to do scholarly research on the topic. It should also indicate why I may be an appropriate advisor for your work, and at least one other faculty member in the department/school who could also advise you given your interests.
    • I receive many emails from prospective students and unfortunately do not have the time to meet with all of them. If you are trying to get a sense for whether I would be a good fit as an advisor, please have a look at my recent publications and talks linked on this page.
  2. Prospective M.S. students
    • I hold a joint appointment in Electrical Engineering & Computer Sciences and the School of Information. These departments have several different M.S. programs. I do not directly admit students into these programs, rather M.S. graduate admissions are handled by a department/school-level committee. If you feel that one of these M.S. programs is a good fit, I encourage you to apply. I do occassionaly work with M.S. students in independent research, but typically only in their second year of study.
  3. Current UC Berkeley graduate students and postdocs
    • Generaly speaking, I am happy to meet with current students to discuss their research or career interests. Send me an email to schedule a time to talk.
  4. Current UC Berkeley undergraduate students
    • I do occassionaly work with undergraduate students in independent research, but typically in their third or fourth year of study. I typically ask for a minimum of a one-year committment.
  5. Non UC Berkeley students
    • Because I receive so many requests from current students, I'm afraid I do not accept non-UCB students for internships or visiting positions.
  6. General advice for prospective Ph.D. students
    • Unlike choosing which university to complete your undergraduate studies, the choice of graduate programs should be guided first by your potential advisor, the quality and reputation of the department, and then the overall institution. The student-advisor relationship, when it works, is incredibly special. When it doesn't work, however, it can be a disaster for everyone. Your advisor will be instrumental in your studies and beyond. Choose an advisor who matches your personality, skills, and interests.
    • In my experience, there are two basic types of advisors: (1) the advisor whose attitude is "the student is here to help further my career; if they learn something along the way or are successful, that is fine"; and (2) the advisor whose attitude is "I am here to advise and mentor this student to help them become a world-class scholar; if they help my career along the way, that is fine." Talk with your potential advisor's current and former students to determine how they treat their students, and if that is the right environment for you.
    • In the U.S., the standard academic ladder consists of four basic steps: Assistant Professor, Associate Professor, Professor (or Full Professor), and Named Professor (e.g., The Jane Doe Professor of Neuroscience).
      • Fresh out of graduate school or postdoc, a faculty member will begin their career as an untenured Assistant Professor. After typically six years or so, they will be considered for promotion and tenure. If all goes well, they will be promoted to Associate Professor with tenure. After another six years or so, they will be considered for promotion to Full Professor (if they are not promoted, they remain at the rank of Associate Professor with their tenure in tact). A select few Full Professors will be granted a named Professorship as a sign of prestige and further excellence.
      • When choosing an advisor, consider the rank of your potential advisor. Young Assistant Professors are great because they are typically at the cutting edge of their field with new ideas, but they have less experience in advising students, and depending on the insitution may not receive tenure at which point they (and possibly you) will not remain at the institution. On the other hand, seasoned Full Professors have more experience advising students, but are often pulled in many directions and so have less time to spend with their students. Associate Professors on their way to Full are in some ways the sweet-spot; they are experienced but still engaged. There are, of course, plenty of exceptions, but do consider where your potential advisor is in their own academic trajectory and how this might impact you.
    • Think carefully about why you are pursuing a Ph.D. There are many good reasons and many less good reasons to puruse a Ph.D. Wanting to pursue an academic career is the typical (but not the only) reason, but be aware that in most fields, there are far more Ph.D. graduates every year than can be absorbed in the academy. Depending on the field, the private, government, and NGO sectors can absorb Ph.D. graduates, but although your degree will open many opportunities, it will also close some opportunities because you may be considered as over-qualified for many entry-level positions. Although the future can be hard to predict, give careful thought to what will come after your Ph.D. and give careful thought if this is the right degree for you. If you are not sure about pursuing a Ph.D., and the five- to six-year committment it will entail, take some time off and work or pursue a M.S. degree.
    • Research done at the highest level is difficult, time-consuming, and more often than not filled with failure and rejection. Research is not a part-time job. If you are not passionate about the problems you are working on, if you get easily frustrated by failure, uncertainty, and endless obstacles, pursuing a Ph.D. Is going to be difficult. The very nature of research is that you are exploring uncharted territory -- if it was easy, someone would likely have already done it. I don't say this to be discouraging, but it is important to be realistic about what lies ahead. Don't think of a Ph.D as an extension of your undergraduate studies, it is qualitatively different in terms of the depth, breadth, and independence that will be required to be successful.
    • Success in a Ph.D. program requires excellence in many different dimensions: deep expertise in your specific area, broad expertise in your general field, great writing and communication skills, independence, curiosity, creativity, and perseverance. Nobody has all of these skills at the highest levels when they begin their studies, and it will take decades to become excellent in all of these areas. Be honest with what you do well and don't do well, and make a concerted effort to build all your skills, even those that may not come naturally.
FUNDING
  1. UC Noyce Initiative, 2023
  2. YouTube, 2023
  3. Adobe, 2023
  4. Meta, 2022
  5. Oak Foundation, 2021
  6. CITRIS & Banatao Institute, 2020
  7. Avast, 2020, 2021
  8. Facebook, 2019
  9. Google, 2019
  10. DARPA (FA8750-16-C-0166), 2016
  11. National Institute of Justice (2016-R2-CX-0012), 2016
  12. Microsoft Corporation, 2016
  13. NVIDIA Corporation, 2015
  14. National Science Foundation (CNS-1205521), 2012
  15. National Science Foundation (DBI-0754773), 2008
  16. National Science Foundation (CNS-0708209), 2007
  17. Department of Homeland Security (2006-CS-001-000001), 2007
  18. John Simon Guggenheim Fellowship, 2006
  19. US Air Force (FA8750-06-C-0011), 2006
  20. National Science Foundation (DEB-0516104), 2005
  21. Bureau of Justice Assistance (2005-DD-BX-1091), 2005
  22. Department of Homeland Security (2000-DT-CX-K001), 2005
  23. Microsoft Corp. 2005, 2006, 2007, 2009
  24. Adobe Systems, Inc., 2004, 2006, 2008
  25. Alfred P. Sloan Fellowship, 2002
  26. National Institute of Justice, 2003
  27. National Institute of Justice (2000-DT-CX-K001), 2000
  28. National Science Foundation CAREER (IIS-99-83806), 1999
  29. National Science Foundation (EIA-98-02068), 1998
digital forensics icon  
DIGITAL FORENSICS
We are developing mathematical and computational techniques to detect various forms of tampering in photos, videos, audios, and documents. We also study the ability of our visual system to perceptually detect photo manipulation.

  BOOK
  1. H. Farid. Fake Photos, MIT Press Essential Knowledge series, 2019. [Publisher] [Amazon]
  2. H. Farid. Photo Forensics. MIT Press, 2016. [Publisher] [Amazon] [Table of Contents, Preface, Introduction]

  SURVEY
  1. H. Farid. Artificial Intelligence: A Primer for Legal Practitioners, in Artificial Intelligence: Legal Issues, Policy, and Practical Strategies, 2024 [chapter]
  2. H. Farid. Image Forensics. Computer Vision: A Reference Guide, 2020. [paper]
  3. H. Farid. Image Forensics. Annual Review of Vision Science, 5(1):549-573, 2019. [paper]
  4. H. Farid. How to Detect Faked Photos. American Scientist, 2017. [paper]
  5. H. Farid. A Survey of Image Forgery Detection. IEEE Signal Processing Magazine, 26(2):16-25, 2009. [paper]
  6. H. Farid. Seeing Is Not Believing. IEEE Spectrum, 46(8):44-48, 2009. [paper]
  7. H. Farid. Photo Fakery and Forensics. In Advances in Computers, Volume 77, Academic Press, 2009. [chapter]
  8. H. Farid. Digital Image Forensics. Scientific American, 298(6):66-71, 2008. [paper]
  9. H. Farid. Digital Doctoring: How to tell the real from the fake. Significance, 3(4):162-166, 2006. [paper]

  DATASET
  1. S. Barrington, M. Bohacek, and H. Farid. DeepSpeak Dataset v1.0, arXiv:2408.05366, 2024. [read] [dataset]

  DEEP FAKES
  1. G.J.A. Porcile, J. Gindi, S. Mundra, J.R. Verbus, and H. Farid, Finding AI-Generated Faces in the Wild. Workshop on Media Forensics at CVPR, 2024. [paper]
  2. M. Bohacek and H. Farid. Lost in Translation: Lip-Sync Deepfake Detection from Audio-Video Mismatch. Workshop on Media Forensics at CVPR, 2024. [paper]
  3. M. Boháček and H. Farid. The Making of an AI News Anchor -- and its Implications. Proceedings of the National Academy of Sciences, 121(1), 2024. [paper]
  4. S. Barrington, R. Barua, G. Koorma, and Hany Farid. Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features. Workshop on Image Forensics and Security, Nuremberg, Germany, 2023. [paper]
  5. Z. Epstein, et al. Art and the Science of Generative AI. Science, 380(6650):1110-1111, 2023. [paper] [extended version]
  6. S. Mundra, G.J.A. Porcile, S. Marvaniya, J.R. Verbus and H. Farid. Exposing GAN-Generated Profile Photos from Compact Embeddings. Workshop on Media Forensics at CVPR, 2023. [paper]
  7. M. Boháček and H. Farid. A Geometric and Photometric Exploration of GAN and Diffusion Synthesized Faces. Workshop on Media Forensics at CVPR, 2023. [paper]
  8. M. Boháček and H. Farid. Protecting World Leaders Against Deep Fakes using Facial, Gestural, and Vocal Mannerisms. Proceedings of the National Academy of Sciences, 119(38), 2022. [paper]
  9. H. Farid. Creating, Using, Misusing, and Detecting Deep Fakes. Journal of Online Trust and Safety, 1(4), 2022. [paper]
  10. H. Farid. Lighting (In)consistency of Paint by Text. arXiv:2207.13744, 2022. [paper]
  11. H. Farid. Perspective (In)consistency of Paint by Text. arXiv:2206.14617, 2022. [paper]
  12. M. Boháček and H. Farid. Protecting President Zelenskyy Against Deep Fakes. arXiv:2206.12043, 2022. [paper]
  13. S.J. Nightingale and H. Farid. AI-Synthesized Faces are Indistinguishable from Real Faces and More Trustworthy. Proceedings of the National Academy of Sciences, 119(8), 2022. [paper]
  14. C. R. Gerstner and H. Farid. Detecting Real-Time Deep-Fake Videos Using Active Illumination. Workshop on Media Forensics at CVPR, 2022. [paper]
  15. S. Agarwal and H. Farid. Detecting Deep-Fake Videos from Aural and Oral Dynamics, Workshop on Media Forensics at CVPR, 2021. [paper]
  16. S. Agarwal, H. Farid, T. El-Gaaly, S. Lim. Detecting Deep-Fake Videos from Appearance and Behavior, IEEE Workshop on Image Forensics and Security, 2020. [paper] [github]
  17. R. Chesney, D. Citron, and H. Farid. All's Clear for Deepfakes: Think Again, Lawfare, 2020. [commentary]
  18. S. Agarwal, H. Farid, O. Fried, and M. Agrawala. Detecting Deep-Fake Videos from Phoneme-Viseme Mismatches, Workshop on Media Forensics at CVPR, 2020. [paper]
  19. N. Carlini and H. Farid. Evading Deepfake-Image Detectors with White- and Black-Box Attacks, Workshop on Media Forensics at CVPR, 2020. [paper]
  20. S. Agarwal, H. Farid, Y. Gu, M. He, K. Nagano, and H. Li. Protecting World Leaders Against Deep Fakes, Workshop on Media Forensics at CVPR, Long Beach, CA, 2019. [paper]

  PHOTO
  1. S. Agarwal and H. Farid. Photo Forensics From Rounding Artifacts, ACM Workshop on Information Hiding and Multimedia Security, Denver CO, 2020. [paper]
  2. W. Fan, S. Agarwal, and H. Farid. Rebroadcast Attacks: Defenses, Reattacks, and Redefenses. European Signal Processing Conference, Rome, Italy, 2018. [paper]
  3. S. Agarwal, W. Fan, and H. Farid. A Diverse Large-Scale Dataset for Evaluating Rebroadcast Attacks. IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Alberta, Canada, 2018. [paper]
  4. S. Agarwal and H. Farid. Photo Forensics from JPEG Dimples. IEEE Workshop on Image Forensics and Security, Rennes, France, 2017. [paper]
  5. W. Fan and H. Farid. A Statistical Prior for Photo Forensics: Object Removal. TR2017-837, Department of Computer Science, Dartmouth College, October 2017. [paper]
  6. S. Pittala, E. Whiting, and H. Farid. A 3-D Stability Analysis of Lee Harvey Oswald in the Backyard Photo. Journal of Digital Forensics, Security and Law, 10(3): 87-98, 2015. [paper]
  7. T. Carvalho, H. Farid, and E. Kee. Exposing Photo Manipulation From User-Guided 3-D Lighting Analysis. SPIE Symposium on Electronic Imaging, San Francisco, CA, 2015. [paper]
  8. E. Kee, J. O'Brien, and H. Farid. Exposing Photo Manipulation from Shading and Shadows. ACM Transactions on Graphics, 33(5):165:1-165:21, 2014. [paper]
  9. E. Kee, J. O'Brien, and H. Farid. Exposing Photo Manipulation with Inconsistent Shadows. ACM Transactions on Graphics, 32(4):28:1-12, 2013. [paper] [talk] [supplemental: 1 | 2 | 3]
  10. M. Kirchner, P. Winkler and H. Farid. Impeding Forgers at Photo Inception. SPIE Symposium on Electronic Imaging, San Francisco, CA, 2013. [paper]
  11. J. O'Brien and H. Farid. Exposing Photo Manipulation with Inconsistent Reflections. ACM Transactions on Graphics, 31(1):4:1-4:11, 2012. [paper]
  12. E. Kee, M. K. Johnson, and H. Farid. Digital Image Authentication from JPEG Headers. IEEE Transactions on Information Forensics and Security, 7(3):1066-1075, 2011. [paper]
  13. E. Kee and H. Farid. Exposing Digital Forgeries from 3-D Lighting Environments. IEEE Workshop on Information Forensics and Security, Seattle, WA, 2010. [paper]
  14. V. Conotter, G. Boato and H. Farid. Detecting Photo Manipulation on Signs and Billboards. International Conference on Image Processing, Hong Kong, 2010. [paper]
  15. E. Kee and H. Farid. Digital Image Authentication from Thumbnails. SPIE Symposium on Electronic Imaging, San Jose, CA, 2010. [paper]
  16. H. Farid. A 3-D Lighting and Shadow Analysis of the JFK Zapruder Film (Frame 317). TR2010-677, Department of Computer Science, Dartmouth College, November 2010. [paper]
  17. H. Farid. A 3-D Photo Forensic Analysis of the Lee Harvey Oswald Backyard Photo. TR2010-669, Department of Computer Science, Dartmouth College, May 2010. [paper]
  18. H. Farid. The Lee Harvey Oswald Backyard Photos: Real or Fake? Perception, 38(11):1731-1734, 2009. [paper]
  19. H. Farid. Exposing Digital Forgeries from JPEG Ghosts. IEEE Transactions on Information Forensics and Security, 4(1):154-160, 2009. [paper]
  20. H. Farid. Digital Doctoring: can we trust photographs? In Deception: From Ancient Empires to Internet Dating, Stanford University Press, 2009. [chapter]
  21. E. Kee and H. Farid. Detecting Photographic Composites of Famous People. TR2009-656, Department of Computer Science, Dartmouth College, October 2009. [paper]
  22. H. Farid. Digital Image Ballistics from JPEG Quantization: A Followup Study. TR2008-638, Department of Computer Science, Dartmouth College, September 2008. [paper]
  23. M.K. Johnson and H. Farid. Exposing Digital Forgeries in Complex Lighting Environments. IEEE Transactions on Information Forensics and Security, 2(3):450-461, 2007. [paper]
  24. M.K. Johnson and H. Farid. Detecting Photographic Composites of People. 6th International Workshop on Digital Watermarking, Guangzhou, China, 2007. [paper]
  25. M.K. Johnson and H. Farid. Exposing Digital Forgeries Through Specular Highlights on the Eye. 9th International Workshop on Information Hiding, Saint Malo, France, 2007. [paper]
  26. H. Farid. Digital Image Ballistics from JPEG Quantization. TR2006-583, Department of Computer Science, Dartmouth College, September 2006. [paper]
  27. H. Farid. Exposing Digital Forgeries in Scientific Images. ACM Multimedia and Security Workshop, Geneva, Switzerland, 2006. [paper]
  28. M.K. Johnson and H. Farid. Exposing Digital Forgeries Through Chromatic Aberration. ACM Multimedia and Security Workshop, Geneva, Switzerland, 2006. [paper]
  29. K. Johnson and H. Farid. Metric Measurements on a Plane from a Single Image. TR2006-579, Department of Computer Science, Dartmouth College, August 2006. [paper]
  30. A.C. Popescu and H. Farid. Exposing Digital Forgeries in Color Filter Array Interpolated Images. IEEE Transactions on Signal Processing, 53(10):3948-3959, 2005. [paper]
  31. A.C. Popescu and H. Farid. Exposing Digital Forgeries by Detecting Traces of Re-sampling. IEEE Transactions on Signal Processing, 53(2):758-767, 2005. [paper]
  32. M.K. Johnson and H. Farid. Exposing Digital Forgeries by Detecting Inconsistencies in Lighting. ACM Multimedia and Security Workshop, New York, NY, 2005. [paper]
  33. A.C. Popescu and H. Farid. Statistical Tools for Digital Forensics. 6th International Workshop on Information Hiding, Toronto, CA, 2004. [paper]
  34. A.C. Popescu and H. Farid. Exposing Digital Forgeries by Detecting Duplicated Image Regions. TR2004-515, Department of Computer Science, Dartmouth College, September 2004. [paper]
  35. H. Farid. Detecting Digital Forgeries Using Bispectral Analysis. MIT AI Memo 1657, June 1999. [paper]

      PERCEPTUAL
  1. A. McGuire, M. Bohacek, H. Farid, P. Taylor, S. Nightingale. How Realistic are AI-generated Faces? European Conference on Visual Perception, 2024 [abstract] [poster]
  2. S.J. Nightingale and H. Farid. AI-Synthesized Faces are Indistinguishable from Real Faces and More Trustworthy. Proceedings of the National Academy of Sciences, 119(8), 2022. [paper]
  3. S.J. Nightingale and H. Farid. Synthetic Faces Are More Trustworthy Than Real Faces. Vision Sciences, 2022. [abstract]
  4. S.J. Nightingale, S. Agarwal, and H. Farid. Perceptual and Computational Detection of Face Morphing. Journal of Vision, 21(3):4, 2021. [paper]
  5. S.J. Nightingale, S. Agarwal, E. Harkonen, J. Lehtinen, and H. Farid. Synthetic Faces: how perceptually convincing are they? Vision Sciences, 2021. [abstract] [poster]
  6. S.J. Nightingale, S. Agarwal, and H. Farid. Can We Detect Face Morphing to Prevent Identity Theft? Vision Sciences, 2020. [abstract] [poster]
  7. S.J. Nightingale, K.A. Wade, H. Farid, and D.G. Watson. Can People Detect Errors in Shadows and Reflections? Attention, Perception, & Psychophysics, 81(8):2917-2943, 2019. [paper]
  8. S.J. Nightingale, K.A. Wade, H. Farid, and D.G. Watson. Can Shadows and Reflections Help in the Detection of Photo Forgeries? Society for Applied Research in Memory and Cognition, Sydney, Australia, 2017. [abstract]
  9. H. Farid and M.J. Bravo. Photo Forensics: How Reliable is the Visual System? Vision Sciences, Naples, FL, 2010. [abstract] [poster]
  10. H. Farid and M.J. Bravo. Image Forensic Analyses that Elude the Human Visual System. SPIE Symposium on Electronic Imaging, San Jose, CA, 2010. [paper]

  VIDEO
  1. V. Conotter, J. O'Brien, and H. Farid. Exposing Digital Forgeries in Ballistic Motion. IEEE Transactions on Information Forensics and Security, 7(1):283-296, 2012. [paper]
  2. W. Wang and H. Farid. Exposing Digital Forgeries in Video by Detecting Double Quantization. ACM Multimedia and Security Workshop, Princeton, NJ, 2009. [paper]
  3. W. Wang and H. Farid. Detecting Re-Projected Video. 10th International Workshop on Information Hiding, Santa Barbara, CA, 2008. [paper]
  4. W. Wang and H. Farid. Exposing Digital Forgeries in Interlaced and De-Interlaced Video. IEEE Transactions on Information Forensics and Security, 2(3):438-449, 2007. [paper]
  5. W. Wang and H. Farid. Exposing Digital Forgeries in Video by Detecting Duplication. ACM Multimedia and Security Workshop, Dallas, TX, 2007. [paper]
  6. H. Farid and J.B. Woodward. Video Stabilization and Enhancement. TR2007-605, Department of Computer Science, Dartmouth College, September 2007. [paper]
  7. W. Wang and H. Farid. Exposing Digital Forgeries in Video by Detecting Double MPEG Compression. ACM Multimedia and Security Workshop, Geneva, Switzerland, 2006. [paper]

  AUDIO
  1. E. A. AlBadawy, S. Lyu, and H. Farid. Detecting AI-Synthesized Speech Using Bispectral Analysis. Workshop on Media Forensics at CVPR, Long Beach, CA, 2019 [paper]
  2. H. Malik and H. Farid. Audio Forensics from Acoustic Reverberation. International Conference on Acoustics, Speech, and Signal Processing, Dallas, TX, 2010. [paper]

      PRINTER
  1. E. Kee and H. Farid. Printer Profiling for Forensics and Ballistics. ACM Multimedia and Security Workshop, Oxford, UK, 2008. [paper]

      CGI or PHOTO?
  1. P. Raiturkar, H. Farid, and E. Jain. Identifying Computer-Generated Portraits: an Eye Tracking Study. Technical Report, University of Florida, 2018. [paper]
  2. B. Mader, M.S. Banks, and H. Farid. Identifying Computer-Generated Portraits: The Importance of Training and Incentives. Perception, 46(9): 1062-1076, 2017. [paper]
  3. O. Holmes, M.S. Banks, and H. Farid. Assessing and Improving the Identification of Computer-Generated Portraits. ACM Transactions on Applied Perception, 13(2):7:1-7:12, 2016. [paper]
  4. V. Conotter, E. Bodnari, G. Boato, and H. Farid. Physiologically-based Detection of Computer Generated Faces in Video. International Conference on Image Processing, Paris, France, 2014. [paper]
  5. H. Farid and M.J. Bravo. Perceptual Discrimination of Computer Generated and Photographic Faces. Digital Investigation, 8:226-235, 2012. [paper]
  6. H. Farid and M.J. Bravo. Photorealistic Rendering: How Realistic Is It? Vision Sciences, Sarasota, FL, 2007. [abstract] [sample images]
  7. S. Lyu and H. Farid. How Realistic is Photorealistic? IEEE Transactions on Signal Processing, 53(2):845-850, 2005. [paper] [code]
  8. H. Farid. Creating and Detecting Doctored and Virtual Images: Implications to The Child Pornography Prevention Act. TR2004-518, Department of Computer Science, Dartmouth College, October 2004. [paper]
  9. H. Farid and S. Lyu. Higher-order Wavelet Statistics and their Application to Digital Forensics. IEEE Workshop on Statistical Analysis in Computer Vision (in conjunction with CVPR), Madison, Wisconsin, 2003. [paper]

      PHOTO RETOUCHING
  1. E. Kee and H. Farid. A Perceptual Metric for Photo Retouching. Proceedings of the National Academy of Sciences, 108(50):19907-19912, 2011. [paper]

      ART
  1. D. Rockmore, S. Lyu and H. Farid. A Digital Technique for Authentication in the Visual Arts. International Foundation for Art Research, (8)2:12-23, 2006. [NA]
  2. S. Lyu, D. Rockmore, and H. Farid. Wavelet Analysis for Authentication. Art + Math = X, Boulder, CO, 2005. [NA]
  3. S. Lyu, D. Rockmore and H. Farid. A Digital Technique for Art Authentication. Proceedings of the National Academy of Sciences, 101(49):17006-17010, 2004. [paper]

      STEGANALYSIS
  1. S. Lyu and H. Farid. Steganalysis Using Higher-Order Image Statistics. IEEE Transactions on Information Forensics and Security, (1)1:111-119, 2006. [paper] [IEEE SPS Best Paper Award, 2010]
  2. M.K. Johnson, S. Lyu and H. Farid. Steganalysis in Recorded Speech. SPIE Symposium on Electronic Imaging, San Jose, CA, 2005. [paper]
  3. S. Lyu and H. Farid. Steganalysis Using Color Wavelet Statistics and One-Class Support Vector Machines. SPIE Symposium on Electronic Imaging, San Jose, CA, 2004. [paper]
  4. S. Lyu and H. Farid. Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines. 5th International Workshop on Information Hiding, Noordwijkerhout, The Netherlands, 2002. [paper]
  5. H. Farid. Detecting Hidden Messages Using Higher-Order Statistical Models. International Conference on Image Processing, Rochester, NY, 2002. [paper] [code]
  6. H. Farid. Detecting Steganographic Messages in Digital Images. TR2001-412, Department of Computer Science, Dartmouth College, September 2001. [paper]

  MISCELLANEOUS
  1. B. Levine, J.J. Kumar, H. Farid, E. Dixon, E. Ikponmwoba. Indications of Child Sexual Abuse Revealed in App Store Reviews. Workshop on Kids' Online Privacy and Safety at SOUPS, Boston, MA, 2022. [paper]
  2. N. Galstyan, J. McCauley, H. Farid, S. Ratnasamy, and S. Shenker. Global Content Revocation on the Internet: A Case Study in Technology Ecosystem Transformation. 20th ACM Workshop on Hot Topics in Networks, Austin, TX, 2022. [paper]
  3. H. Farid. An Overview of Perceptual Hashing. Journal of Online Trust and Safety, 1(1), 2021. [paper]
  4. P. Singh and H. Farid. Robust Homomorphic Image Hashing. Workshop on Media Forensics at CVPR, Long Beach, CA, 2019. [paper]
  5. H. Farid. The Dystopian Digital Future of Fake Media, Quartz, 2018. [commentary]
  6. H. Farid. Digital Forensics in a Post-Truth Age. Forensic Science International, 289: 268-269, 2018. [commentary]

      MUSINGS
  1. Deepfakes in the 2024 Presidential Election [link]
  2. How good are you at detecting AI-generated voices? Take the quiz
  3. How good are you at detecting AI-generated faces? Take the quiz
  4. Tips for recognizing deepfake faces
  5. Photographs with sharks are almost always fake (in fact, I'm not sure anymore if sharks are even real).


forensic science icon  
FORENSIC SCIENCE
We are studying the accuracy and reliability of photographic forensic techniques that are used to identify people, and predictive algorithms used in the criminal justice system.

  1. J. Norman and H. Farid. An Investigation into the Impact of AI-Powered Image Enhancement on Forensic Facial Recognition. Workshop on Media Forensics at CVPR, 2024. [paper]
  2. J. Norman, S. Agarwal, and H. Farid. An Evaluation of Forensic Facial Recognition. arXiv:2311.06145, 2023. [paper]
  3. S. Barrington and H. Farid. A Comparative Analysis of Human and AI Performance in Forensic Estimation of Physical Attributes. Scientific Reports, 13(4784), 2023. [paper]
  4. S. Barrington and H. Farid. Perceptual Estimates of the Physical Attributes of People in Photographs. Vision Sciences, 2023. [abstract] [poster]
  5. N. Thakkar, G. Pavlakos and H. Farid. The Reliability of Forensic Body-Shape Identification. Workshop on Media Forensics at CVPR, 2022. [paper]
  6. N. Thakkar and H. Farid. On the Feasibility of 3D Model-Based Forensic Height and Weight Estimation, Workshop on Media Forensics at CVPR, 2021. [paper]
  7. J. Dressel and H. Farid. The Dangers of Risk Prediction in the Criminal Justice System. MIT Case Studies in Social and Ethical Responsibilities of Computing, February, 2021. [paper]
  8. S. J. Nightingale and H. Farid. Assessing the Reliability of a Clothing-Based Forensic Identification. Proceedings of the National Academy of Sciences, 117(20):5176-5183, 2020. [paper]
  9. B. Lorch, S. Agarwal, and H. Farid. Forensic Reconstruction of Severely Degraded License Plates, IS&T Electronic Imaging, San Francisco, CA, 2019. [paper] [github]
  10. J. Dressel and H. Farid. The Accuracy, Fairness, and Limits of Predicting Recidivism, Science Advances, 4(1):eaao5580, 2018. [paper]
  11. S. Agarwal, D. Tran, L. Torresani, and H. Farid. Deciphering Severely Degraded License Plates. SPIE Symposium on Electronic Imaging, San Francisco, CA 2017. [paper]
misinformation icon  
MISINFORMATION
We are studying the spread and promotion of mis- and disinformation, as well as techniques to disrupt its spread.

  1. E. Booth, J. Lee, M.A. Rizoiu, and H. Farid. Conspiracy, Misinformation, Radicalisation: Understanding the online pathway to indoctrination and opportunities for intervention. Journal of Sociology, 2024. [paper]
  2. E. Waissbluth, H. Farid, V. Sehgal, A. Peshin, and S. Afroz. Domain-Level Detection and Disruption of Disinformation. arXiv: 2205.03338, 2022. [paper]
  3. H. Farid. On Algorithmic Amplification (in response to "Disinformed"), Inference, 6(1), 2021. [letter]
  4. V. Sehgal, A. Peshin, S. Afroz, and H. Farid. Mutual Hyperlinking Among Misinformation Peddlers. arXiv: 2104.11694, 2021. [paper]
  5. M. Faddoul, G. Chaslot, and H. Farid. A Longitudinal Analysis of YouTube's Promotion of Conspiracy Videos. arXiv: 2003.03318, 2020. [paper]
  6. S.J. Nightingale and H. Farid. Examining the Global Spread of COVID-19 Misinformation. arXiv: 2006.08830, 2020. [paper]
image analysis icon  
IMAGE ANALYSIS
We have developed techniques for discrete multi-dimensional differentiation [3, 4, 8], blind removal of luminance and geometric distortions [5, 6, 7] and the design of steerable filters [9, 10].

  1. S. Agarwal and H. Farid. A JPEG Corner Artifact from Directed Rounding of DCT Coefficients. TR20018-838, Department of Computer Science, Dartmouth College, February 2018. [paper]
  2. H. Farid and J. Kosecka. Estimating Planar Surface Orientation Using Bispectral Analysis. IEEE Transactions on Image Processing, 16(8):2154-2160, 2007. [paper]
  3. H. Farid and E.P. Simoncelli. Differentiation of Discrete Multi-Dimensional Signals. IEEE Transactions on Image Processing, 13(4):496-508, 2004. [paper] [code]
  4. H. Farid. Discrete-Time Fractional Differentiation from Integer Derivatives. TR2004-528, Department of Computer Science, Dartmouth College, December 2004. [paper] [code]
  5. H. Farid. Blind Inverse Gamma Correction. IEEE Transactions on Image Processing, 10(10):1428- 1433, 2001. [paper] [code]
  6. H. Farid and A.C. Popescu. Blind Removal of Lens Distortions. Journal of the Optical Society of America, 18(9):2072-2078, 2001. [paper]
  7. H. Farid and A.C. Popescu. Blind Removal of Image Non-Linearities. International Conference on Computer Vision (ICCV), Vancouver, Canada, 2001. [paper]
  8. H. Farid and E.P. Simoncelli. Optimally Rotation-Equivariant Directional Derivative Kernels. Computer Analysis of Images and Patterns (CAIP), Kiel, Germany, 1997. [paper]
  9. E.P. Simoncelli and H. Farid. Steerable Wedge Filters for Local Orientation Analysis. IEEE Transactions on Image Processing, 5(9):1377-1382, 1996. [paper]
  10. E.P. Simoncelli and H. Farid. Steerable Wedge Filters. International Conference on Computer Vision (ICCV), Boston, MA, 1995. [paper]


human perception icon  
HUMAN PERCEPTION
We study various aspects of the human visual system, including mechanisms governing search and recognition in cluttered scenes [2-22, 25, 29, 32] and a critique of the theory of temporal synchrony for perceptual grouping [23, 24, 26, 31, 33]. See also "perceptual" and "CGI or photo?" entries under "digital forensics"

  1. E.A. Cooper, R. Casati, H. Farid, and P. Cavanagh. The Art of the Float. Journal of Vision, 23(8):13, 2023. [paper]
  2. M.J. Bravo and H. Farid. Observers Change their Target Template Based on Expected Context. Attention, Perception, & Psychophysics, 78(3):829-837, 2016. [paper]
  3. M.J. Bravo and H. Farid. Search Templates Can be Adapted to the Context, but Only for Unfamiliar Targets. Vision Sciences, St. Pete Beach, FL, 2014. [abstract] [poster]
  4. M.J. Bravo and H. Farid. Informative Cues Can Slow Search: The cost of matching a specific template. Attention, Perception, & Psychophysics, 76(1):32-39, 2014. [paper]
  5. M.J. Bravo and H. Farid. Task Demands Determine the Specificity of the Search Template. Attention, Perception, & Psychophysics, 74(1):124-131, 2012. [paper]
  6. M.J. Bravo and H. Farid. Symbolic Distractor Cues Facilitate Search. Vision Sciences, Naples, FL, 2012. [abstract] [poster]
  7. M.J. Bravo and H. Farid. Distinctive Features are Prominent in Object Representations. Vision Sciences, Naples, FL, 2011. [abstract] [poster]
  8. M.J. Bravo and H. Farid. The Specificity of the Search Template. Journal of Vision, 9(1):34, 1-9, 2009. [paper]
  9. M.J. Bravo and H. Farid. Training Determines the Target Representation for Search. Vision Sciences, Naples, FL, 2009. [abstract]
  10. M.J. Bravo and H. Farid. A Scale Invariant Measure of Image Clutter. Journal of Vision, 8(1):1-9, 2008. [paper] [code]
  11. M.J. Bravo and H. Farid. The Depth of Distractor Processing in Search with Clutter. Perception, 36(6):821-829, 2007. [paper]
  12. M.J. Bravo and H. Farid. A Measure of Relative Set Size for Search in Clutter. Vision Sciences, Sarasota, FL, 2007. [abstract]
  13. M.J. Bravo and H. Farid. Object Recognition in Clutter. Perception & Psychophysics, 68(6):911- 918, 2006. [paper]
  14. V. Maljkovic, P. Martini and H. Farid. The Contribution of Statistical Image Differences to Human Rapid Categorization of Natural Scenes is Negligible. Vision Sciences, Sarasota, FL, 2006. [abstract]
  15. M.J. Bravo and H. Farid. Using an Interest Point Detector to Find Potential Fragments for Recognition. Vision Sciences, Sarasota, FL, 2006. [abstract]
  16. M.J. Bravo and H. Farid. The Depth of Distractor Processing in Search Through Clutter. Vision Sciences, Sarasota, FL, 2005. [abstract]
  17. M.J. Bravo and H. Farid. Search For a Category Target in Clutter. Perception, 33:643-652, 2004. [paper]
  18. M.J. Bravo and H. Farid. Recognizing and Segmenting Objects in Clutter. Vision Research, 44(4):385-396, 2004. [paper]
  19. M.J. Bravo and H. Farid. Still Searching a Cluttered Scene. Vision Sciences, Sarasota, FL, 2004. [abstract]
  20. V. Maljkovic, P. Martini and H. Farid. The Time-Course of Categorization of Real-Life Scenes with Affective Content. Vision Sciences, Sarasota, FL, 2004. [abstract]
  21. M.J. Bravo and H. Farid. Object Segmentation by Top-Down Processes. Visual Cognition, 10(4):471-491, 2003. [paper]
  22. M.J. Bravo and H. Farid. Searching a Cluttered Scene. Vision Sciences, Sarasota, FL, 2003. [abstract]
  23. H. Farid. Temporal Synchrony in Perceptual Grouping: A Critique. Trends in Cognitive Sciences, 6(7):284-288, 2002. [paper]
  24. H. Farid and E.H. Adelson. Energy versus Synchrony in Perceptual Grouping. Vision Sciences, Sarasota, FL, 2002. [abstract]
  25. M.J. Bravo and H. Farid. Segmentation in Clutter. Vision Sciences, Sarasota, FL, 2002. [abstract]
  26. H. Farid and E.H. Adelson. Synchrony Does Not Promote Grouping in Temporally Structured Displays. Nature Neuroscience, 4(9):875-876, 2001. [paper] [supplemental: videos]
  27. M.J. Bravo and H. Farid. Texture Perception on Folded Surfaces. Perception, 30(7):819-832, 2001. [paper]
  28. R. van Ee, B. Anderson, and H. Farid. Occlusion Junctions do not Improve Stereoacuity. Spatial Vision, 15(1):45-49, 2001. [paper]
  29. M.J. Bravo and H. Farid. Top-Down and Bottom-Up Processes for Object Segmentation. Vision Sciences, Sarasota, FL, 2001. [abstract]
  30. M.J. Bravo and H. Farid. Effects of 3D Structure on Motion Segmentation. Vision Research, 40(6):695-704, 2000. [paper]
  31. H. Farid and E.H. Adelson. Standard Mechanisms Can Explain Grouping in Temporally Synchronous Displays. Investigative Opthalmology and Visual Science, Fort Lauderdale, FL, 2000. [abstract]
  32. M.J. Bravo and H. Farid. The Role of Object Recognition in Scene Segmentation. Investigative Opthalmology and Visual Science, Fort Lauderdale, FL, 2000. [abstract]
  33. E.H. Adelson and H. Farid. Filtering Reveals Form in Temporally Structured Displays. Science, 286:2231, 1999. [paper]
  34. M.J. Bravo and H. Farid. Texture Segmentation in 3D. Investigative Opthalmology and Visual Science, Fort Lauderdale, FL, 1999. [abstract]
  35. M.J. Bravo and H. Farid. The Effects of 2D and 3D Smoothness on Motion Segmentation. Investigative Opthalmology and Visual Science, Fort Lauderdale, FL, 1998. [abstract]
  36. H. Farid, E.P. Simoncelli, M.J. Bravo and P.R. Schrater. Effects of Contrast and Period on Perceived Coherence of Moving Square-Wave Plaids (evidence for a speed bias in the human visual system). Investigative Opthalmology and Visual Science, Fort Lauderdale, FL, 1995. [abstract]
  37. H. Farid and E.P. Simoncelli. The Perception of Transparency in Moving Square-Wave Plaids. Investigative Opthalmology and Visual Science, Sarasota, FL, 1994. [abstract]


computer vision icon  
COMPUTER VISION
We have developed techniques to reconstruct extremely low-quality images of license plates [1,2], separate reflections [3, 4], optically estimate range [5-8] and experience telepresence [9-11].

  1. B. Lorch, S. Agarwal, and H. Farid. Forensic Reconstruction of Severely Degraded License Plates, IS&T Electronic Imaging, San Francisco, CA, 2019 [paper] [github]
  2. S. Agarwal, D. Tran, L. Torresani, and H. Farid. Deciphering Severely Degraded License Plates. SPIE Symposium on Electronic Imaging, San Francisco, CA 2017. [paper]
  3. H. Farid and E.H. Adelson. Separating Reflections from Images by use of Independent Components Analysis. Journal of the Optical Society of America, 16(9):2136-2145, 1999. [paper] [code]
  4. H. Farid and E.H. Adelson. Separating Reflections and Lighting in Images Using Independent Components Analysis. Computer Vision and Pattern Recognition (CVPR), June 1999. [paper] [code]
  5. H. Farid and E.P. Simoncelli. Range Estimation by Optical Differentiation. Journal of the Optical Society of America, 15(7): 1777-1786, 1998. [paper]
  6. H. Farid. Range Estimation by Optical Differentiation, Department of Computer and Information Science, Univerisity of Pennsylvania, 1997. [dissertation]
  7. H. Farid and E.P. Simoncelli. A Differential Optical Range Camera. Optical Society of America, Rochester, NY, 1996. [paper]
  8. E.P. Simoncelli and H. Farid. Direct Differential Range Estimation Using Optical Masks. European Conference on Computer Vision (ECCV), Cambridge, UK, 1996. [paper]
  9. H. Fuchs, G. Bishop, K. Arthur, L. McMillan, R. Bajcsy, S.W. Lee, H. Farid and T. Kanade. Virtual Space Teleconferencing Using a Sea of Cameras. First International Symposium on Medical Robotics and Computer Assisted Surgery, Pittsburgh, PA, 1994. [paper]
  10. K. Arthur, G. Bishop, R. Bajcsy, H. Farid, H. Fuchs, S.W. Lee, L. McMillan and A. State. Virtual Reality and Telepresence for 21st Century Remote Medical Consultation. Second Carolina Conference in Biomedical Engineering, 1994. [NA]
  11. H. Farid, S.W. Lee, and R. Bajcsy. View Selection Strategies for Multi-View, Wide-Baseline Stereo. Technical Report, Department of Computer Science, University of Pennsylvania, 1994. [paper]
medical imaging icon  
MEDICAL IMAGING
We have developed techniques to register medical imagery [1, 5, 8, 12, 13, 14] and perform image-guided neurosurgery [2, 3, 4, 6, 9, 10].

  1. S. Periaswamy and H. Farid. Medical Image Registration with Partial Data. Medical Image Analysis, 10:452-464, 2006. [paper] [code]
  2. H. Sun, K.E. Lunn, H. Farid, Z. Wu, D.W. Roberts, A. Hartov and K.D. Paulsen. Stereopsis-Guided Brain Shift Compensation. IEEE Transactions on Medical Imaging, 24(8):1039-1052, 2005. [NA]
  3. H. Sun, D.W. Roberts, H. Farid, Z. Wu, A. Hartov and K.D. Paulsen. Cortical Surface Tracking Using a Stereoscopic Operating Microscope. Neurosurgery, 56:86-97, 2005. [abstract]
  4. H. Sun, H. Farid, D.W. Roberts, K. Rick, A. Hartov, and K.D. Paulsen. A Non-Contacting 3-D Digitizer for Use in Image-Guided Neurosurgery. Steroetactic and Functional Neurosurgery, 80(1-4):120-124, 2003. [paper]
  5. S. Periaswamy and H. Farid. Elastic Registration in the Presence of Intensity Variations. IEEE Transactions on Medical Imaging, 22(7):865-874, 2003. [paper]
  6. H. Sun, H. Farid, K. Rick, A. Hartov, D.W. Roberts, and K.D. Paulsen. Estimating Cortical Surface Motion Using Stereopsis for Brain Deformation Models. Medical Image Computing & Computer Assisted Intervention (MICCAI), Montreal, Canada, 2003. [paper]
  7. J. Ford, H. Farid, F. Makedon, L.A. Flashman, T.W. McAllister, V. Megalooikonomou, and A.J. Saykin. Patient Classification of fMRI Activation Maps. Medical Image Computing & Computer Assisted Intervention (MICCAI), Montreal, Canada, 2003. [paper]
  8. S. Periaswamy and H. Farid. Elastic Registration with Partial Data. Second International Workshop on Biomedical Image Registration, Philadelphia, PA, 2003. [paper]
  9. H. Sun, H. Farid D. Roberts, K. Rick, A. Kartov, and K. Paulsen. A Non-contacting 3-D Digitizer For Use in Image-Guided Neurosurgery. American Society for Stereotactic and Functional Neurosurgery, New York City, 2003. [abstract]
  10. H. Sun, H. Farid, A. Hartov, K.E. Lunn, D.W. Roberts, K.D. Paulsen. Real-time Correction Scheme for Calibration and Implementation of Microscope-based Image-guided Neurosurgery. SPIE's International Symposium on Medical Imaging, San Diego, CA, 2002. [NA]
  11. S. Inati, H. Farid, K. Sherwin, and S. Grafton. A Global Probabilistic Approach to Fiber Tractography with Diffusion Tensor MRI. Human Brain Mapping, Brighton, UK, 2001. [abstract]
  12. J.B. Weaver, S. Periaswamy, H. Farid, D.N. Rockmore, C.J. Kasales, W. Black, and D.M. Healy Jr. Lesion Size Estimation Using Warped Registration of Interval Images. International Society for Magnetic Resonance in Medicine, 2001. [NA]
  13. S. Periaswamy and H. Farid. Differential Elastic Image Registration. TR2001-413, Department of Computer Science, Dartmouth College, September 2001. [paper]
  14. S. Periaswamy, J.B. Weaver, D.M. Healy Jr., D. Rockmore, P.J. Kostelec, and H. Farid. Differential Affine Motion Estimation for Medical Image Registration. SPIE's 45th Annual Meeting, San Diego, CA, 2000. [paper]
computational biology icon  
COMPUTATIONAL BIOLOGY
We have developed techniques to automatically analyze circadian plant rhythms [1,2], wildlife photographs [3-5], the 3-D structure of Damselflies [6-8], mass spectrometry data for cancer screening [9], and design and predict protein structure [10, 11].

  1. K. Greenham, P. Lou, J.R. Puzey, G. Kumar, C. Arnevik, H. Farid, J. H. Willis, and C.R McClung. Geographic Variation of Plant Circadian Clock Function in Natural and Agricultural Settings. Journal of Biological Rhythms, 32(1):26-34, 2016. [paper]
  2. K. Greenham, P. Lou, S. E. Remsen, H. Farid, and C.R McClung. TRiP: Tracking Rhythms in Plants, an automated leaf movement analysis program for circadian period estimation. Plant Methods, 11(33):1-11, 2015. [paper]
  3. D.T. Bolger, T.A. Morrison, B. Vance, D. Lee, and H. Farid. A Computer-Assisted System for Photographic Mark-Recapture Analysis. Methods in Ecology and Evolution, 3(5):813-822, 2012. [paper] [supplemental] [code]
  4. D.T. Bolger, T. Morrison, B. Vance and H. Farid. Development and Application of a Computer-Assisted System for Photographic Mark-Recapture Analysis. Ecological Society of America, Pittsburgh, PA, 2010. [abstract] [code]
  5. D.T. Bolger, T. Morrison, B. Vance and H. Farid. A New Software Application for Photographic Mark Recapture Analysis. Society for Conservation Biology, Edmonton Alberta, Canada, 2010. [abstract] [code]
  6. L. Shen, H. Farid and M.A. McPeek. Modeling 3-Dimensional Morphological Structures using Spherical Harmonics. Evolution, 63(4):1003-1016, 2009. [paper] [code]
  7. M.A. McPeek, L. Shen and H. Farid. The Correlated Evolution of 3-Dimensional Reproductive Structure Between Male and Female Damselflies. Evolution, 63(1):73-83, 2009. [paper] [code]
  8. M.A. McPeek, L. Shen, J.Z. Torrey and H. Farid. The Tempo and Mode of 3-Dimensional Morphological Evolution in Male Reproductive Structures. American Naturalist, 171(5):E158-E178, 2008. [paper] [code]
  9. R.H. Lilien, H. Farid and B.R. Donald. Probabilistic Disease Classification of Expression-Dependent Proteomic Data from Mass Spectrometry of Human Serum. Journal of Computational Biology, 10(6):925-946, 2003. [paper] [code]
  10. X. Jiang, H. Farid, E. Pistor and R.S. Farid. A New Approach to the Design of Uniquely Folded Thermally Stable Proteins. Protein Science, 9:403-416, 2000. [paper]
  11. P.S. Shenkin, H. Farid and J.S. Fetrow. Prediction and Evaluation of Side-chain Conformations for Protein Backbone Structures. Proteins: Structure, Function and Genetics, 26:323-352, 1996. [paper]
miscellaneous icon  
MISCELLANEOUS
Reining in online absuses [2], general public's vs. on-line user's understanding of science [3], quantifying geologic surfaces [4, 7, 8], building 3-D topographical maps [10, 11], 3-D reconstruction of ancient Egyptian tombs [12, 13, 14] and the Jose Clemente Orozco murals [15], math for kids [16], and science for kids [17].

  1. E.A. Cooper and H. Farid. A Toolbox for the Radial and Angular Marginalization of Bivariate Normal Distributions. arXiv: 2005.09696, 2020. [paper] [github]
  2. H. Farid. Reining in Online Abuses. Technology and Innovation, 19(3): 593-599, 2018. [paper]
  3. E.A. Cooper and H. Farid. Does the Sun Revolve Around the Earth? A Comparison between the General Public and On-line Survey Respondents in Basic Scientific Knowledge. Public Understanding of Science, 25(2):146-153, 2016. [paper] [supplemental]
  4. D. Finnegan, G. Hamilton, L. Stearns, A. LeWinter, H. Farid, and H. Renedo. Tidewater Glacier Velocities from Repeat Ground-Based Terrestrial LiDAR Scanning; Helheim Glacier, Southeast Greenland. Transactions of the American Geophysical Union, San Francisco, CA, 2014. [abstract]
  5. H. Farid. Digital Imaging, Encyclopedia of Perception, 2009. [entry]
  6. H. Farid. Photography Changes What We are Willing to Believe, Smithsonian Photography Initiative: Click! Photography Changes Everything, 2008. [entry]
  7. D.C. Finnegan, H. Farid, D.E. Lawson and W. Krabill. Quantifying Surface Fluctuations using Optical Flow Techniques and Multi-Temporal LiDAR. Transactions of the American Geophysical Union, San Francisco, CA, 2006. [abstract]
  8. H. Farid and D.C. Finnegan. Quantifying Planetary and Terrestrial Geologic Surfaces Using Wavelet Statistics. Transactions of the American Geophysical Union, San Francisco, CA, 2005. [abstract]
  9. J.E. Dobson, J.B. Woodward, S.A. Schwarz, J.C. Marchesini, H. Farid, and S.W. Smith. The Dartmouth Green Grid. Workshop on High Performance Computing in Academia, Atlanta, GA, 2005. [paper]
  10. A. Heimsath and H. Farid. Hillslope Topography from Unconstrained Photographs. Mathematical Geology, 34(8):929-952, 2002. [paper]
  11. A.M. Heimsath and H. Farid. Hillslope Topography from Unconstrained Photographs. Transactions of the American Geophysical Union, San Francisco, CA, 2002. [abstract]
  12. H. Farid and S. Farid. Unfolding Sennedjem's Tomb. KMT: A Modern Journal of Ancient Egypt, 12(1):46-59, 2001. [paper] [images]
  13. H. Farid. Reconstructing Ancient Egyptian Tombs. The International Symposium on Virtual and Augmented Architecture, Dublin, Ireland, 2001. [paper] [images]
  14. Egypt: 3-D reconstruction of ancient Egyptian tombs. [link]
  15. Orozco: 3-D reconstruction of Jose Clemente Orozco's murals. [link]
  16. Math Kids: learn how mathematics can enter into nearly every corner of your life. [link]
  17. Science Kids: providing answers to some of those perplexing questions about Science and Nature. [link]


My Paul Erdös number is 2 [Erdös → Winkler → Farid]
  1. [Erdös, Suen, Winkler. "On the size of a random maximal graph," Random Structures & Algorithms, 1995]
  2. [Kirchner, Winkler, Farid. "Impeding forgers at photo inception," SPIE, 2013]

My Kevin Bacon number is 3 [Bacon → Belcher → Nice → Farid]
  1. [Kevin Bacon & Patricia Belcher, "Flatliners"]
  2. [Patricia Belcher & Chuck Nice, "The Week of"]
  3. [Chuck Nice & Hany Farid, "Is It True?"]