Protecting world leaders against deep fakes using facial, gestural, and vocal mannerisms
Open accessAbstract
Since their emergence a few years ago, artificial intelligence (AI)-synthesized media-so-called deep fakes-have dramatically increased in quality, sophistication, and ease of generation. Deep fakes have been weaponized for use in nonconsensual pornography, large-scale fraud, and disinformation campaigns. Of particular concern is how deep fakes will be weaponized against world leaders during election cycles or times of armed conflict. We describe an identity-based approach for protecting world leaders from deep-fake imposters. Trained on several hours of authentic video, this approach captures distinct facial, gestural, and vocal mannerisms that we show can distinguish a world leader from an impersonator or deep-fake imposter.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent advances in technology for hyper-realistic manipulations to video pose a threat to traditional standards of evidence and trust in media.
“Recent advances in technology for algorithmically applying hyper-realistic manipulations to video are simultaneously enabling new forms of interpersonal communication and posing a threat to traditional standards of evidence and trust in media1–8.”
From Human detection of political speech deepfakes across transcripts, audio, and video (2024) · cites this paper as [8]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 17 · Cited by 45
Research works printed but not linked: 13
- [5]P. Zhou, X. Han, V. I. Morariu, L. S. Davis, Two-stream neural networks for tampered face detection., International Conference on Computer Vision and Pattern Recognition (2017).
- [6]L. Li, Face X-ray for more general face forgery detection. http://arxiv.org/abs/1912.13458 (2019). · arXiv
- [7]Y. Li, In ictu oculi: Exposing AI created fake videos by detecting eye blinking., International Workshop on Information Forensics and Security pp. 1– 7. (2018).
- [8]S. Agarwal, H. Farid, O. Fried, M. Agrawala, Detecting deep-fake videos from phoneme-viseme mismatches in CVPR Workshop on Media Forensics. pp. 660– 661. (2020).
- [9]S. Agarwal, Protecting world leaders against deep fakes in CVPR Workshop on Media Forensics. 1. (2019).
- [10]D. Cozzolino, A. Rössler, J. Thies, M. Nießner, L. Verdoliva, ID-reveal: Identity-aware deepfake video detection in International Conference on Computer Vision. pp. 15108– 15117. (2021).
- [11]A. Rössler, FaceForensics++: Learning to detect manipulated facial images in International Conference on Computer Vision and Pattern Recognition. (2019).
- [12]T. Baltrusaitis, A. Zadeh, Y. C. Lim, L. P. Morency, Openface 2.0: Facial behavior analysis toolkit in IEEE International Conference on Automatic Face& Gesture Recognition. pp. 59– 66. (2018).
- [13]R. Gross, I. Matthews, J. Cohn, T. Kanade, S. Baker, Multi-pie in IEEE International Conference on Automatic Face& Gesture Recognition. pp. 1– 8. (2008). PMC2873597 20490373
- [15]V. Bazarevsky, Blazepose: On-device real-time body pose tracking. http://arxiv.org/abs/2006.10204 (2020). · arXiv
- [17]M. Boháček, M. Hrúz, Sign pose-based transformer for word-level sign language recognition in IEEE/CVF Winter Conference on Applications of Computer Vision Workshops. pp. 182– 191. (2022).
- [18]A. Bauer, The Use of Signing Space in a Shared Sign Language of Australia (De Gruyter, ed. 1, 2014).
- [19]S. Davis, P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28, 357– 366 (1980).
- Authors
- Bohacek, M., & Farid, H.
- Affiliations
- Gymnasium of Johannes Kepler
- University of California System (US)
- Corresponding author
- Farid, Hany
- ORCID
- Farid, Hany
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2022-11-23
- Volume
- 119
- Issue
- 48
- Pages
- e2216035119-e2216035119
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC9860138
- OpenAlex
- W4309825539
- Cited by
- 45
- References
- 17
- Citations by year
- 2026: 9 · 2025: 12 · 2024: 13 · 2023: 11
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- deepfakes, world leaders, identity verification, AI-generated content, disinformation, impersonation detection
- MeSH terms
- Artificial Intelligence, Gestures, Deception
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
