用强化学习生成可解释的伪造图像数据，提升检测模型泛化能力。
Explainable Deepfake Detection with RL Enhanced Self-Blended Images
- 基于自融合图像构建思维链数据，自动标注伪造痕迹
- 强化学习优化生成过程，跨数据集检测准确率超主流方法
- 适合需要可解释性与低标注成本的AI安全研究者
现有深度伪造检测方法普遍缺乏可解释输出。随着多模态大语言模型（MLLM）兴起，研究者开始探索其在可解释检测中的应用，但主要障碍在于高质量带细粒度伪造标注的数据集稀缺——文本标注成本高且困难，尤其对高保真伪造图像或视频。此外，多项研究表明强化学习（RL）能显著提升视觉任务性能，尤其增强跨域泛化能力。为降低标注成本并推动主流MLLM框架在该任务中的应用，我们提出一种基于自融合图像的自动化思维链（CoT）数据生成框架，以及一个强化学习增强的深度伪造检测框架。大量实验验证了我们的CoT数据构建流程、定制奖励机制及反馈驱动的合成数据生成方法的有效性。所提方法在多个跨数据集基准上达到与当前最优（SOTA）方法相当的性能。实现细节见 https://github.com/deon1219/rlsbi。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。