用检索增强与强化学习提升多模态模型的造假检测能力
VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
- 结合RAG与强化学习动态获取伪造知识
- 在多个数据集上达到领先性能，泛化能力更强
- 适合需要可解释检测的AI安全研究者
在深度伪造检测任务中，现有基于多模态大模型的方法主要分为两类：与小型检测器互补组合，或静态注入伪造知识。缺乏专业伪造知识限制了这些检测模型的表现。为此，我们深入探讨两个关键问题：如何为多模态大模型提供高质量的关联伪造知识？如何在存在噪声参考信息的情况下赋予模型批判性推理能力？我们尝试通过融合检索增强生成（RAG）与强化学习（RL）给出初步解答。基于此，提出了VRAG-DFD框架，具备精准动态知识检索与强大批判性推理能力。具体而言，在数据层面，构建了两个RAG驱动的数据集：用于伪造知识标注的取证知识库（FKD），以及用于构建批判性思维链的取证思维链数据集（F-CoT）。在模型训练方面，采用三阶段训练流程（对齐->监督微调->GRPO）逐步培养模型的推理能力。实验表明，该方法在深度伪造检测泛化测试中达到最先进（SOTA）及具有竞争力的性能。
原文摘要 · Abstract (English)
In Deepfake Detection (DFD) tasks, researchers proposed two types of MLLM-based methods: complementary combination with small DFD detectors, or static forgery knowledge injection. The lack of professional forgery knowledge hinders the performance of these DFD-MLLMs. To solve this, we deeply considered two insightful issues: How to provide high-quality associated forgery knowledge for MLLMs? AND How to endow MLLMs with critical reasoning abilities given noisy reference information? Notably, we attempted to address above two questions with preliminary answers by leveraging the combination of Retrieval-Augmented Generation (RAG) and Reinforcement Learning (RL). Through RAG and RL techniques, we propose the VRAG-DFD framework with accurate dynamic forgery knowledge retrieval and powerful critical reasoning capabilities. Specifically, in terms of data, we constructed two datasets with RAG: Forensic Knowledge Database (FKD) for DFD knowledge annotation, and Forensic Chain-of-Thought Dataset (F-CoT), for critical CoT construction. In terms of model training, we adopt a three-stage training method (Alignment->SFT->GRPO) to gradually cultivate the critical reasoning ability of the MLLM. In terms of performance, VRAG-DFD achieved SOTA and competitive performance on DFD generalization testing.
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。