DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection

TL;DR

DVAR introduces a debate-based, reasoning framework for video authenticity detection that enhances generalization and interpretability over traditional pattern-matching methods.

Contribution

It presents a training-free, multi-agent debate system incorporating logical reasoning and knowledge bases to improve robustness and transparency in video forgery detection.

Findings

DVAR achieves competitive accuracy with state-of-the-art supervised methods.

It generalizes better to unseen video generation architectures.

The framework provides explicit reasoning traces for detection decisions.

Abstract

The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to generalize beyond their training distributions. To address this, we propose DVAR (Debate-based Video Authenticity Reasoning), a training-free framework that reformulates video detection as a structured multi-agent forensic reasoning process. Moving beyond the paradigm of pattern matching, DVAR orchestrates a competition between a Generative Hypothesis Agent and a Natural Mechanism Agent. Through iterative rounds of cross-examination, these agents defend their respective explanations against abnormal evidence, driving a logical convergence where the truth emerges from rigorous stress-testing. To adjudicate these conflicting claims, we apply Occam's Razor through the Minimum Description Length (MDL) framework, defining an Explanatory Cost to quantify the "logical burden" of each reasoning path. Furthermore, we integrate GenVideoKB, a dynamic knowledge repository that provides high-level reasoning heuristics on generative boundaries and failure modes. Extensive experiments demonstrate that DVAR achieves competitive performance against supervised state-of-the-art methods while exhibiting superior generalization to unseen generative architectures. By transforming detection into a transparent debate, DVAR provides explicit, interpretable reasoning traces for robust video authenticity assessment.