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

Authors: Shuhan Xia, Peipei Li, Xuannan Liu, Dongsen Zhang, Xinyu Guo, Zekun Li

Published: 2025-11-26 10:33:12+00:00

AI Summary

AVFakeBench is introduced as the first comprehensive audio-video forgery detection benchmark, featuring 12K questions covering seven multi-modal forgery types and four annotation levels across human and general subjects. The benchmark utilizes a hybrid forgery framework to ensure high quality and is used to evaluate 11 AV-LMMs and 2 expert detectors. Results demonstrate AV-LMMs' potential as unified detectors but expose significant limitations in fine-grained perception and explanatory reasoning.

Abstract

The threat of Audio-Video (AV) forgery is rapidly evolving beyond human-centric deepfakes to include more 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 introduce AVFakeBench, the first comprehensive audio-video forgery detection benchmark that spans rich forgery semantics across both human subject and general subject. AVFakeBench comprises 12K carefully curated audio-video questions, covering seven forgery types and four levels of annotations. To ensure high-quality and diverse forgeries, we propose a multi-stage hybrid forgery framework that integrates proprietary models for task planning with expert generative models for precise manipulation. The benchmark establishes a multi-task evaluation framework covering binary judgment, forgery types classification, forgery detail selection, and explanatory reasoning. We evaluate 11 Audio-Video Large Language Models (AV-LMMs) and 2 prevalent detection methods on AVFakeBench, demonstrating the potential of AV-LMMs as emerging forgery detectors while revealing their notable weaknesses in fine-grained perception and reasoning.