Defending Deepfake via Texture Feature Perturbation
This addresses the problem of social trust and information security threats from Deepfakes, offering a proactive defense method, though it is incremental as it builds on existing perturbation-based approaches.
The paper tackles the challenge of detecting Deepfakes by proactively inserting invisible perturbations into facial texture features, which distorts Deepfake generation and causes visual defects, as demonstrated on CelebA-HQ and LFW datasets.
The rapid development of Deepfake technology poses severe challenges to social trust and information security. While most existing detection methods primarily rely on passive analyses, due to unresolvable high-quality Deepfake contents, proactive defense has recently emerged by inserting invisible signals in advance of image editing. In this paper, we introduce a proactive Deepfake detection approach based on facial texture features. Since human eyes are more sensitive to perturbations in smooth regions, we invisibly insert perturbations within texture regions that have low perceptual saliency, applying localized perturbations to key texture regions while minimizing unwanted noise in non-textured areas. Our texture-guided perturbation framework first extracts preliminary texture features via Local Binary Patterns (LBP), and then introduces a dual-model attention strategy to generate and optimize texture perturbations. Experiments on CelebA-HQ and LFW datasets demonstrate the promising performance of our method in distorting Deepfake generation and producing obvious visual defects under multiple attack models, providing an efficient and scalable solution for proactive Deepfake detection.