Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples

Shehzeen Hussain, Paarth Neekhara, Malhar Jere, Farinaz Koushanfar, Julian McAuley; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 3348-3357

Abstract


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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Hussain_2021_WACV, author = {Hussain, Shehzeen and Neekhara, Paarth and Jere, Malhar and Koushanfar, Farinaz and McAuley, Julian}, title = {Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {3348-3357} }