ADA-FInfer: Inferring Face Representations From Adaptive Select Frames for High-Visual-Quality Deepfake Detection

Interpretable deepfake detection is gaining attention for providing explainable, trustworthy results, avoiding the limitations of ‘black-box’ models. Current interpretable methods focus on visible artifacts in low-visual-quality deepfakes, but these artifacts become less apparent in high-visual-quality deepfakes generated by advanced models. With advancements in deep generative models, producing high-visual-quality deepfakes has become a strategy to evade detection. To address this, we propose <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula>, an adaptive frame selection and interpretable face representation inference method for detecting high-visual-quality deepfakes. <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> adaptively selects frames by analyzing optical flow to reveal manipulations. We also introduce an adaptive attack method that manipulates specific frames, and our adaptive selection strategy shows resistance to such attacks. <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> uses an encoder to learn face representations from source and target faces, applying a representation-prediction loss to maximize the distinction between real and fake videos. To provide further insights, we employ the joint entropy, mutual information, and conditional entropy analyses to explain the method's effectiveness. Extensive experiments and ablation studies demonstrate that <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> achieves promising performance in detecting high-visual-quality deepfakes.