Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning
This addresses the critical issue of adversarial robustness in deepfake detection for security and media authenticity applications, representing an incremental improvement over existing defense methods.
The paper tackles the problem of adversarial attacks on deepfake detection models by introducing Adversarial Feature Similarity Learning (AFSL), which integrates deep feature learning paradigms to distinguish real from fake instances and maximize similarity between perturbed and unperturbed examples, resulting in significant outperformance over standard adversarial training-based defenses on datasets like FaceForensics++.
Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new challenge in the form of adversarial attacks. Adversaries can manipulate deepfake videos with small, imperceptible perturbations that can deceive the detection models into producing incorrect outputs. To tackle this critical issue, we introduce Adversarial Feature Similarity Learning (AFSL), which integrates three fundamental deep feature learning paradigms. By optimizing the similarity between samples and weight vectors, our approach aims to distinguish between real and fake instances. Additionally, we aim to maximize the similarity between both adversarially perturbed examples and unperturbed examples, regardless of their real or fake nature. Moreover, we introduce a regularization technique that maximizes the dissimilarity between real and fake samples, ensuring a clear separation between these two categories. With extensive experiments on popular deepfake datasets, including FaceForensics++, FaceShifter, and DeeperForensics, the proposed method outperforms other standard adversarial training-based defense methods significantly. This further demonstrates the effectiveness of our approach to protecting deepfake detectors from adversarial attacks.