Adversarial Threats to DeepFake Detection: A Practical Perspective

Paarth Neekhara, Brian Dolhansky, Joanna Bitton, Cristian Canton Ferrer; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 923-932

Abstract


Facially manipulated images and videos or DeepFakes can be used maliciously to fuel misinformation or defame individuals. Therefore, detecting DeepFakes is crucial to increase the credibility of social media platforms and other media sharing web sites. State-of-the-art DeepFake detection techniques rely on neural network based classification models which are known to be vulnerable to adversarial examples. In this work, we study the vulnerabilities of state-of-the-art DeepFake detection methods from a practical standpoint. We perform adversarial attacks on DeepFake detectors in a black box setting where the adversary does not have complete knowledge of the classification models. We study the extent to which adversarial perturbations transfer across different models and propose techniques to improve the transferability of adversarial examples. We also create more accessible attacks using Universal Adversarial Perturbations which pose a very feasible attack scenario since they can be easily shared amongst attackers. We perform our evaluations on the winning entries of the DeepFake Detection Challenge (DFDC) and demonstrate that they can be easily bypassed in a practical attack scenario by designing transferable and accessible adversarial attacks.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Neekhara_2021_CVPR, author = {Neekhara, Paarth and Dolhansky, Brian and Bitton, Joanna and Ferrer, Cristian Canton}, title = {Adversarial Threats to DeepFake Detection: A Practical Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {923-932} }