Protecting President Zelenskyy against Deep Fakes

TL;DR

This paper presents a behavioral model based on facial and gestural cues to verify the authenticity of President Zelenskyy's videos, aiming to combat deep-fake disinformation during conflicts.

Contribution

It introduces a novel behavioral model trained on authentic videos to distinguish Zelenskyy from deep-fake imposters, enhancing disinformation detection.

Findings

Model trained on 8+ hours of authentic video

Successfully distinguishes real Zelenskyy from deep-fakes

Potential tool for real-time disinformation verification

Abstract

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.