Explainable Deepfake Detection with RL Enhanced Self-Blended Images

TL;DR

This paper introduces an RL-enhanced deepfake detection framework utilizing Self-Blended Images for automated data generation, achieving competitive results and addressing interpretability and data annotation challenges in deepfake detection.

Contribution

It proposes a novel RL-based framework with Self-Blended Images for automated data creation, improving deepfake detection performance and interpretability.

Findings

Effective CoT data construction pipeline validated

Reward mechanism enhances synthetic data quality

Achieves competitive results on multiple benchmarks

Abstract

Most prior deepfake detection methods lack explainable outputs. With the growing interest in multimodal large language models (MLLMs), researchers have started exploring their use in interpretable deepfake detection. However, a major obstacle in applying MLLMs to this task is the scarcity of high-quality datasets with detailed forgery attribution annotations, as textual annotation is both costly and challenging - particularly for high-fidelity forged images or videos. Moreover, multiple studies have shown that reinforcement learning (RL) can substantially enhance performance in visual tasks, especially in improving cross-domain generalization. To facilitate the adoption of mainstream MLLM frameworks in deepfake detection with reduced annotation cost, and to investigate the potential of RL in this context, we propose an automated Chain-of-Thought (CoT) data generation framework based on Self-Blended Images, along with an RL-enhanced deepfake detection framework. Extensive experiments validate the effectiveness of our CoT data construction pipeline, tailored reward mechanism, and feedback-driven synthetic data generation approach. Our method achieves performance competitive with state-of-the-art (SOTA) approaches across multiple cross-dataset benchmarks. Implementation details are available at https://github.com/deon1219/rlsbi.