Key points are not available for this paper at this time.
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.
Building similarity graph...
Analyzing shared references across papers
Loading...
Matyáš Boháček
Hany Farid
Proceedings of the National Academy of Sciences
University of California, Berkeley
Johannes Kepler University of Linz
University Ucinf
Building similarity graph...
Analyzing shared references across papers
Loading...
Boháček et al. (Wed,) studied this question.
www.synapsesocial.com/papers/6a086a4fab15ea61dee8d38d — DOI: https://doi.org/10.1073/pnas.2216035119