Search papers, labs, and topics across Lattice.
This paper introduces a Training-Free Dual-System (TFDS) framework to improve self-supervised talking head forgery detection by better exploiting the discriminative capacity of existing detectors. TFDS uses a threshold-based routing mechanism (System 1) to separate confident and uncertain samples based on anomaly scores, then refines the ordering of uncertain samples using evidence-guided reasoning (System 2). Experiments show TFDS consistently improves performance across datasets by correcting the ordering of ambiguous samples, revealing untapped potential in current self-supervised detectors.
Even without retraining, a simple dual-system approach can significantly boost the performance of self-supervised talking head forgery detectors by refining the ordering of uncertain samples.
Supervised talking head forgery detection faces severe generalization challenges due to the continuous evolution of generators. By reducing reliance on generator-specific forgery patterns, self-supervised detectors offer stronger cross-generator robustness. However, existing research has mainly focused on building stronger detectors, while the discriminative capacity of trained detectors remains insufficiently exploited. In particular, for score-based self-supervised detectors, the limited discriminative ability on hard cases is often reflected in unreliable anomaly ordering, leaving room for further refinement. Motivated by this observation, we draw inspiration from the dual-system theory of human cognition and propose a Training-Free Dual-System (TFDS) framework to further exploit the latent discriminative capacity of existing score-based self-supervised detectors. TFDS treats anomaly-like scores as the basis of System-1, using lightweight threshold-based routing to partition samples into confident and uncertain subsets. System-2 then revisits only the uncertain subset, performing fine-grained evidence-guided reasoning to refine the relative ordering of ambiguous samples within the original score distribution. Extensive experiments demonstrate consistent improvements across datasets and perturbation settings, with the gains arising mainly from corrected ordering within the uncertain subset. These findings show that existing self-supervised talking head forgery detectors still contain underexploited discriminative cues that can be effectively unlocked through training-free dual-system reasoning.
