Protecting President Zelenskyy against Deep Fakes
This addresses the disinformation problem for the public and authorities during the 2022 Russian invasion of Ukraine, though it is incremental as it applies an existing method to a specific new case.
The researchers tackled the problem of detecting deep-fake videos of Ukrainian President Zelenskyy by developing a facial and gestural behavioral model trained on over eight hours of authentic video, which can distinguish Zelenskyy from deep-fake imposters.
The 2022 Russian invasion of Ukraine is being fought on two fronts: a brutal ground war and a duplicitous disinformation campaign designed to conceal and justify Russia's actions. This campaign includes at least one example of a deep-fake video purportedly showing Ukrainian President Zelenskyy admitting defeat and surrendering. In anticipation of future attacks of this form, we describe a facial and gestural behavioral model that captures distinctive characteristics of Zelenskyy's speaking style. Trained on over eight hours of authentic video from four different settings, we show that this behavioral model can distinguish Zelenskyy from deep-fake imposters.This model can play an important role -- particularly during the fog of war -- in distinguishing the real from the fake.