AI RESEARCH

AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs

arXiv CS.CV

ArXi:2511.21251v3 Announce Type: replace The threat of Audio-Video (AV) forgery is rapidly evolving beyond human-centric deepfakes to include diverse manipulations across complex natural scenes. However, existing benchmarks are still confined to DeepFake-based forgeries and single-granularity annotations, thus failing to capture the diversity and complexity of real-world forgery scenarios. To address this, we