XAI-DRIVEN VIDEO FORGERY FORENSICS: A UNIFIED EXPLAINABLE AI FRAMEWORK FOR MULTI-TYPE VIDEO MANIPULATION DETECTION

Abstract

Video forgeries are more threatening and become a serious challenge for digital forensics. Multi-type of video forgeries with the help of AI is more challenging in digital trust and forensics.  Deep learning models can expose and classify manipulated videos with high accuracy and efficiency. But, they rarely explain their decisions in applications like courtrooms, media investigations and legal proceedings. This paper presents XAI-VFF, a unified Explainable AI framework that combines Gradient-weighted Class Activation Mapping (Grad-CAM), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME) for video forgery explanations. This developed with the intention to produce pixel-precise, forensically admissible explanations for multi-type video forgeries at both inter-frame and intra-frame levels. A novel metric, the Forensic Explanation Coverage Score (FECS), is introduced to quantify explanation quality. Experiments on FaceForensics++, DFDC, Celeb-DF v2, and SYSU-OBJFORG show that XAI-VFF achieves a mean FECS of 0.847, Grad-CAM IoU of 0.794, and LIME fidelity of 0.891 across five forgery categories. The framework gives explanations on multi-type video forgeries with no hallucination risk, making it practical for real forensic workflows.