Exposing Vulnerabilities of Deepfake Detection Systems with Robust Attacks
Authors:
Open Access
- 7 February 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 3 (3) , 1-23
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. 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. 1Keywords
This publication has 24 references indexed in Scilit:
- Synthesizing ObamaACM Transactions on Graphics, 2017
- Two-Stream Neural Networks for Tampered Face Detection2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Transferable Deep-CNN Features for Detecting Digital and Print-Scanned Morphed Face Images2017
- Towards Evaluating the Robustness of Neural Networks2017
- Practical Black-Box Attacks against Machine Learning2017
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- Counter-Forensics: Attacking Image Forensics2012