TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
Year: 2025
Type: preprint
Abstract: Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trust. Detecting such person-driven manipulations requires systems that not only distinguish altered content from authentic media but also provide clear and reliable reasoning. In this paper, we introduce TriDF, a comprehensive benchmark for interpretable DeepFake detection. TriDF contains high-quality forgeries from advanced synthesis models, covering 16 DeepFake types across image, video, and audio modalities. The benchmark evaluates three key aspects: Perception, which measures the ability of a model to identify fine-grained manipulation artifacts using human-annotated evidence; Detection, which assesses classification performance across diverse forgery families and generators; and Hallucination, which quantifies the reliability of model-generated explanations. Experiments on state-of-the-art multimodal large language models show that accurate perception is essential for reliable detection, but hallucination can severely disrupt decision-making, revealing the interdependence of these three aspects. TriDF provides a unified framework for understanding the interaction between detection accuracy, evidence identification, and explanation reliability, offering a foundation for building trustworthy systems that address real-world synthetic media threats.
Source: arXiv (Cornell University)
Authors: Jiang-Lin, Jian-Yu, Huang, Kang-Yang, Zou, Ling, Lo, Ling, Yang, Sheng-Ping, Tseng, Yu-Wen, Lin, Kun-Hsiang, Chen, Chia-Ling, Ta, Yu-Ting, Wang, Yan-Tsung, Chen, Po-Ching, Xie, Hongxia, Shuai, Hong-Han, Cheng, Wen-Huang
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417296392
Cites:
Cited by:
Related to: