Exposing Vulnerabilities of Deepfake Detection Systems with Robust Attacks

Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake videos has garnered immense interest in academia and industry. Recently developed Deepfake detection methods rely on Deep Neural Networks (DNNs) to distinguish AI-generated fake videos from real videos. In this work, we demonstrate that it is possible to bypass such detectors by adversarially modifying fake videos synthesized using existing Deepfake generation methods. We further demonstrate that our adversarial perturbations are robust to image and video compression codecs, making them a real-world threat. We present pipelines in both white-box and black-box attack scenarios that can fool DNN-based Deepfake detectors into classifying fake videos as real. Finally, we study the extent to which adversarial perturbations transfer across different Deepfake detectors and create more accessible attacks using universal adversarial perturbations that pose a very feasible attack scenario since they can be easily shared amongst attackers.1