Yao, S. et al. 2026. Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 33 (Mar. 2026), 27764–27772. DOI:https://doi.org/10.1609/aaai.v40i33.39998.