siwei lyu image

Siwei Lyu, Ph.D., FIEEE, FIAPR [Google Scholar] [DBLP]

SUNY Distinguished Professor, Empire Innovation Professor
Director, Institute for AI and Data Science (IAD)
Director, UB Media Forensic Lab (UB MDFL)
University at Buffalo, State University of New York
Phone: (716) 437-1587
Email: siweilyu AT buffalo DOT edu
Office: 313 Davis Hall, Buffalo, NY14260

    • (08/25/2025) Xuanyi Zhou and Shengan Shi have successfully completed their stay at UBMDL as undergraduate interns. Good luck, Xuanyi and Shengan!

      Lab lunch 2025

    • (08/18/2025) The book I co-edited, "Truth-Seeking in an Age of (Mis)Information Overload", is featured as the CHOICE review of the week [Link].
    • (08/15/2025) Congratulations to Zhaofeng for his paper (co-authored with Prof. Kaiyi Ji, Yifang Yang, and Dr. Shu Hu) receiving the Best Paper Award at the GLOW Workshop of IJCAI 2025.
    • (08/11/2025) I delivered a keynote speech at the 21st IEEE AVSS Conference in Tainan, Taiwan.

      Lab lunch 2025

    • (07/15/2025) Our lab had a successful year at ICCV 2025, with two papers in the regular conference and four papers in the workshops. Congratulations to all authors!
    • (06/19/2025) Yan Ju successfully defended her PhD thesis today. Congratulations, Dr. Ju! She will go on to work as a Data Scientist at Walmart.
    • (06/15/2025) Congratulations to Yu Cai and Shan Jia for their paper [IHMMSEC25] winning the Best Student Paper Award.
    • (04/29/2025) I was promoted to SUNY Distinguished Professor. I would not have achieved this recognition without my colleagues, students, and mentors. I am immensely grateful to everyone who has helped me in my career to date.
    • (04/07/2025) Our lab presented at the SUNY AI Summit at the UB campus and was featured in the SUNY Provost's report to the SUNY Board of Trustees.

      SUNY AI Summit 2025 photo 1

      SUNY AI Summit 2025 photo 2

    • (04/09/2025) My student Soumyya Datta was interviewed for his work on detecting deepfakes by local Channel 2 TV [Link]. Nice job, Soumyya!
    • (03/31/2025) Our K-12 article, "Detecting deepfakes: how can we ensure that generative AI is used for good?", was hand-picked by the TES resources content team to be featured in March 2025 [Link].
    • (09/26/2024) Dr. Defang Chen joined UB MDFL as a post-doc and serves as the Assistant Lab Director. Welcome on board, Defang!
    • (09/26/2024) After working in UB MDFL as Assistant Lab Director for three years, Dr. Shan Jia will join Google as a Research Scientist. Congratulations, Shan!
    • (09/25/2024) This year our lab has THREE papers accepted to NeurIPS! [NEURIPS24A] [NEURIPS24B] [NEURIPS24C]
    • (09/20/2024) I testified at the NY State Assembly Public Hearing on the Impact of AI on Consumer Safety and Privacy. Read the UB News Story.
    • Our work on DeepFake detection received continuous attention from media:

      12/18/23 Logically Facts 01/08 The Register, 01/09 New York Times, 01/10 Reuters, 1/12 Techstory, 1/16 Futurum magazine, 1/18 Boomlive, 1/23 Nature (Chinese translation: Weixin), 1/23 National Desk, 1/25 VerifyThis, 1/26 Newsweek, 1/29 become AIIA Fellow, 2/1 Washington Post, 2/15 Communications of ACM, 2/20 New Scientist, 2/21 CBC Kids, 3/4 Worldtimetodays, 3/4 SciAM, 3/14 PolitiFact, 4/19 NHK.

    • (12/12/2023) Yan Ju received the UB CSE Department's Graduate Research Award. Congratulations to Yan!
    • (12/05/2023) Our recent work on Improving Fairness in DeepFake Detection is introduced in this video. [Link]
    • (11/26/2023) University at Buffalo News has a story featuring our research work at UB Media Forensic Lab and Center for Information Integrity [Link]
    • (11/13/2023) Our work is featuresd on NPR: AI Deepfake
    • (11/07/2023) Our work is featuresd on USA Today: Altered Kelly Clarkson video promotes keto diet gummies fact check
    • (11/01/2023) Our work is featuresd on AFT Fact Check: AFP Fact Check
    • (09/28/2023) Our work is featuresd on Reuters: Image of Senator Rand Paul in red bathrobe is AI-generated
    • (09/28/2023) Our work is featuresd on the Communications of ACM [Link to article]
    • (09/26/2023) Our work is featuresd on AFT Fact Check: [Link]
    • (09/27/2023) Our work is featuresd on AFT Fact Check: [Link]
    • (09/09/2023) Our work is featuresd on Spectrum News: Understanding Artificial Intelligence's Role in Society
    • (08/02/2023) Our work is featuresd on Reuters: Fact check: Photo of JFK and his body double is not authentic
    • (06/05/2023) Our work is featuresd on Wall Street Journal: Chatbots Banter AI Forever Voices
    • (05/23/2023) Our work is featuresd on Verifythis: Pentagon explosion fake photo possibly AI-generated fact check
    • (05/15/2023) Our work is featuresd on 10TV/Verify: Verify: Siwei Lyu Expert Interview
    • (04/20/2023) Our work is featuresd on National Geographic Magazine: How can you tell if a photo is AI-generated? Here are some tips
    • (04/15/2023) Our work is featuresd on Salon: Deepfake videos are so convincing—and so easy to make—that they pose a political
    • (04/06/2023) Our work is featuresd on Newsweek: Deepfakes AI Photos Videos Misinformation Guide
    • (03/24/2023) Our work is featuresd on Newsweek: Deepfakes Could Destroy 2024 Election
    • (02/10/2023) Our work is featuresd on Reuters: Fact check: Video does not show Joe Biden making transphobic remarks
    • (01/20/2023) Our work is featuresd on AFT Fact Check: AFP Fact Check
    • (12/06/2022) I became a Distinguished Member of the Association of Computing Machinery (ACM) Link.
    • (09/12/2022) I become a Fellow of Asia-Pacific Artificial Intelligence Association AAIA.
    • (06/28/2022) University at Buffalo's news release on the establishment of Center for Information Integrity [Link].
    • (06/23/2022) I am honored and humbled to be elavated to the IAPR Fellow of Class 2022.
    • (05/24/2022) Receiving my IEEE Fellow pin at the 2022 ICASSP Conference from IEEE Signal Processing Society President.

      lab 08/15

    • (05/09/2022) I sat down with Rachel and Eric at the ForcePoint Cybersecurity Podcast to talk about DeepFakes and the future [Link].
    • (05/06/2022) Lipeng Ke has successfully defended his thesis. Congratulations, Dr. Ke! Lipeng will take position at Amazon.
    • (04/26/2022) I was interviewed by MSNBC News on a recent DeepFake case [Link] and TheStreet.com [Link].
    • (04/23/2022) Shu Hu has successfully defended his thesis. Congratulations, Dr. Hu! Shu will take a post-doc position at Carneige Mellon University.
    • (04/14/2022) I had a good conversation with Kerry Tomlinson of Ampere News about DeepFakes [Part 1] and [YouTube Video -- Part 1], and [Part 2] and [YouTube Video -- Part 2]
    • (04/04/2022) Our paper on "Sum of Ranked Range Loss for Supervised Learning" is accepted by Journal of Machine Learning Research [JMLR22].
    • (03/15/2022) Our work on DeepFake detection has a particular timely meaning: see the recent reports on our work [Report1] and [Report2].
    • (02/17/2022) I was invited to give a talk at Bug.out [Video Link].
    • (02/07/2022) Our work on "Combating AI-Synthesized Media beyond Detection" has been funded by NSF SaTC [NSF Project Page].
    • (01/29/2022) I am appointed as an Associate Editor for the IEEE Transactions on Multimedia.
    • (01/21/2022) We have three papers accepted to ICASSP 2022 [ICASSP22a][ICASSP22b][ICASSP22c]!
    • (12/01/2022) We have two papers accepted to AAAI 2022 [AAAI22a][AAAI22b]!
    • (11/23/2021) I am honored and humbled to be elavated to the IEEE Fellow of Class 2022 [Link]. I would like to thank my students, post-docs, colleagues, collaborators, and friends for their support!
    • (10/15/2021) UB estabhlishes the Center for Information Integrity (CII) to promote multi-disciplinary research in the area of mis/disinformation. I will serve as the founding Director along with Prof. David Castillo of the Roman Language Department.
    • (10/02/2021) I am the receipient of the IEEE Region 1 (Northeastern US) Technological Innovation (Academic) Award for contributions in technologies that counter DeepFakes.
    • (09/23/2021) The NSF Convergence Accelerator Phase 1 Project with me as the Principal Investigator has been awarded by the National Science Foundation, more details see the UB News Release. [Link]
    • (09/01/2021) Our lab continues to grow. Dr. Shan Jia will join my lab as a new post-doc, and Mingzhen Huang joins my lab as a Ph.D., FIEEE, FIAPR student.
    • (08/06/2021) I gave a keynote speech at the 2021 International Joint Conference on Biometrics (IJCB 2021)
    • (07/26/2021) I was featured in an online article on fake face generation [Link].
    • (06/18/2021) I was invited to give a Keynote speech at the CVPR Workshop on Multimedia Forensics on our work of using corneal spectral highlights to detect GAN synthesized faces. [Link to video].
    • (06/08/2021) With my former student/post-doc Yuezun Li, I gave a tutorial at ICASSP 2021 on DeepFake Generation and Detection [Part 1] [Part 2]. [Part 3].
    • (03/15/2021) Our work on detecting GAN generated images using corneal reflections is reported by UB News. [Link]. This work has also been featured on WKBW-TV [Link].
    • (01/29/2021) I appeared on the Interview by Newsy Cable Network and talked about my work on DeepFake forensics. [Link].
    • (12/09/2020) My work on DeepFake detection is listed as one of the "Four AI technologies that could transform the way we live and work" in a Nature article. [Link].
    • (11/18/2020) I was interviewed by Fox News Cleveland on my work of DeepFake detection. [Link].
    • (11/01/2020) Our open-platform for DeepFake detection, DeepFake-o-meter is online now. [Link].
    • (08/11/2020) I was interviewed by BYU Radio "The Lisa Show" to discuss DeepFakes [Link].
    • (07/20/2020) I was featured in a Scientific American Program on DeepFakes [Link], accompanied by a SciAm blog piece written by me [Link].
    • (06/15/2020) Yuezun Li successfully defended his thesis, Congratulations Dr. Li! Yuezun is the sixth Ph.D., FIEEE, FIAPR student I graduated, along with Xunyu Pan (2011), Amanda Fernandez (2013), Yueming Yang (2014), Xin Wang (2015), and Wenbo Li (2019).
    • (05/26/2020) I was interviewed by Japanese TV Channel NHK's Koukusai Houdou (国際報道) for our work on DeepFake detection [Link].
    • (02/24/2020) Our paper on the [Celeb-DF dataset], which includes 5000+ high-quality synthetic videos has been accepted by CVPR 2020!
    • (02/24/2020) I was featured in Episode 6 of the PBS Documentary "Fake: Searching for Truth in the Age of Misinformation" [Link].
    • (01/30/2020) I was interviewed by Inverse [Link].
    • (01/28/2020) I presented and spoke as a panelist at the FTC workshop on voice cloning technologies [Link] and corresponding report on VentureBeat [Link].
    • (01/08/2020) I was interviewed Fox News about Facebooks's new policy on DeepFakes [Link].
    • (11/26/2019) My comments were featured in an article in the Wired Magazine UK [Link].
    • (11/22/2019) I testified at New York State Senate Hearing on protecting consumer data and privacy on online platforms [Link].
    • (10/09/2019) I was featured in an IEEE Spectrum article [Link].
    • (10/04/2019) I discussed DeepFakes and their detections on WHYY The Pulse [Link].
    • (09/26/2019) I testified at the US House of Representative Committee on Science, Space, and Technology Subcommittee on Oversights and Investigation Hearing on "Online Imposter and Disinformation" Link. See also report on Times Union [Link] and Washington Post [Link].
    • (09/03/2019) I am very excited to be an academic advisor of the DeepFake Detection Challenge sponsored by FaceBook, Microsoft and PAI with multiple universities, along with Profs Hany Farid and Alyosha Efros (UC-Berkeley), Serge Belongie (Cornell Tech), Rama Chellappa (John Hopkins), Phil Torr (Oxford), Phillip Isola and Antonio Torraalba (MIT) [Link]. See also report on Times Union [Link].
    • (07/25/2019) Wenbo Li successfully defended his thesis on Human Pose Estimation and Activity Recognition. Wenbo will join Samsung Research Lab USA as a Research Scientist. Congratulations Dr. Li!
    • (07/11/2019) I was interviewed by Brooklyn Eagles to discuss our work on detecting DeepFakes [Link to story].
    • (06/25/2019) I have written an article on The Conversation about our work of detecting and protecting from DeepFakes [Link].
    • (06/02/2019) Our work on detecting DeepFakes continues to draw attention and is featured on Full Measure with Sharyl Atkison [Link to video] and on Brazil news media O Globo [Link].
    • (05/13/2019) Our work has been covered by Fox News [Link], USA Today [Link] and Chinese National TV (CCTV) [Link].
    • (05/02/2019) Two papers on Digital Media Forensics are accepted by Workshop on Information Hiding and Multimedia Security (IHMMSec2019) in Paris.
    • (05/01/2019) Our lab keeps growing: Dr. Feng Ding joins as a post-doc, Ehab AlBadawy joins as a Ph.D., FIEEE, FIAPR student, and Ao Luo joins as a visiting student.
    • (04/17/2019) I gave a presentation at O'Reilly AI Conference at NYC [link].
    • (03/01/2019) Our work is featured on Spanish News paper El Pais [link].
    • (02/28/2019) Our work on detecting AI-synthesized fake media has won Google Faculty Research Award for the year of 2019.
    • (02/14/2019) Our work is featured on O'Reily's Data Show Podcast [link] and a Brookings Institute blog [link].
    • (02/01/2019) Our work on detecting DeepFake is featured on Univision [link].
    • (11/19/2018) I received SUNY Chancellor's Award for Research and Creative Activities. Here is a photo at the ceremony.

      Chancellor Award 2018

      (left to right) President Havidàn Rodríguez, Dr. Siwei Lyu, and Dean Kim Boyer.

    • (11/06/2018) Our work on detecting DeepFake generated videos using detection of eye blinking are reported by many news media, including The MIT Technology Review [article], CNN Money [article], Spectrum News [TV interview] Wired Magazine [article], UBuffalo Podcast [interview], Data Skeptic Podcast [interview], Deseret News [article], The Register [article], Columnbia Journalism Review [article], iNews [article]
      • For details, check my article on The Conversation and our paper to be presented at WIFS 18.
    • (09/01/2018) Our pose estimation work is ranked #1 on the very challenging MPII benchmark.
      Video demonstration of our pose estimation results. This work has also been accepted for publication by ECCV.
    • (02/18/2018) I talked about detecting Deep Fakes on Science Friday with Ira Flatlow [interview].
    • (09/06/2017) Paper on Average Top-K Learning is accepted by NIPS 2017.
    • (07/29/2017) I co-organized and participated the IEEE/Nvidia AI City Challenge with the IEEE Smart City Conference 2017. and our team got honary mention.
    • (07/19/2017) Ppaper on using RNN-Tree for Skeleton-based Action Recognition is accepted by ICCV 2017.
    • (07/17/2017) I co-organized the 2017 AVSS Challenge on Advance Traffic Monitoring, and co-organize the International Workshop on Traffic and Street Surveillance and Safety (IWT4S), in conjunction with the 2017 IEEE Conference on Advances in Video and Signal-based Survillance (AVSS).
    • (03/21/2017) I am awarded SUNY Buffalo’s Presidential Award for Excellence in Research and Creative Activities.
    • (02/01/2017) I will be serving as an Area Chair for IEEE International Conference for Image Processing (ICIP) 2017 in Beijing, China.
    • (12/06/2016) I will be serving on IEEE SPS Information Forensics and Security Technical Committee from 2017 to 2019.
    • (10/01/2016) I will be serving as an Associate Editor for IEEE Transactions on Information Forensics and Security from 2016 to 2019.
    • (09/01/2016) I am elevated to IEEE Senior Member.
    • (08/15/2016) Yueming Yang successfully defended his thesis. He also present his work at AVSS 2016 at Colorado Springs. Congratulations, Dr. Yang!