This work introduces the first large-scale benchmark for this task by collecting real portraits and fake portraits from multiple sources and evaluates representative existing detectors on this benchmark, revealing their lack of explicit mechanisms for retaining fine-grained information and maintaining feature consisten...
Yu-Jie Gao, Zijian Yu, Yan Hong et al.· 0 citations
AI-generated image manipulation localization identifies edited pixels, but its OOD performance lags behind image-level detection partly because pixel supervision entangles forensic evidence with dataset-specific mask geometry and semantic boundaries. Extending image-level distribution alignment to localization, we cons...
Haozhen Yan, Siyuan Shan, Zijian Yu et al.· 0 citations
Defake-o3 is presented, an explainable AIGI detector that moves from speculative rationales to verifiable evidence, and Experiments show that Defake-o3 improves both detection accuracy and explanation quality, producing more localized, verifiable, and persuasive evidence.
Bowen Deng, Jiahui Zhan, Yikun Ji et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.