CORE: 面向冲突的通用多模态篡改检测推理
CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
AI总结：
提出CORE框架，通过构建冲突归因语料库和面向冲突的推理，增强多模态大语言模型的冲突捕捉能力，实现鲁棒且泛化的多模态篡改检测。
摘要：
生成式AI的快速崛起使得多模态假新闻日益逼真且泛滥，对公众信任和社会稳定构成严重威胁。现有检测方法严重依赖针对特定篡改的模型和大规模标注数据，导致对新兴篡改类型的泛化能力差。我们观察到，篡改误导信息的本质在于其内在冲突，即跨模态或与常识世界知识之间的语义或物理不一致。受此启发，我们提出面向冲突的推理（CORE）框架，这是一种有效的范式，通过学习赋予多模态大语言模型（MLLMs）显式的冲突捕捉能力。为此，CORE首先构建了冲突归因语料库（CAC），包含冲突因素和来源的细粒度标注，为后续的冲突感知训练提供必要的数据支持。通过基于CAC进行面向冲突的表示增强和推理，CORE实现了鲁棒且可泛化的冲突检测，能够有效且快速地适应未见过的篡改类型，仅需少量样本甚至零样本设置。大量实验表明，CORE超越了现有最先进模型。数据集和代码已公开于该链接。
英文摘要：
The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability. Existing detection methods rely heavily on manipulation-specific models and large-scale labeled data, resulting in poor generalization to emerging manipulation types. We observed that the essence of manipulated misinformation lies in its intrinsic conflicts, \textbf{i.e.,} semantic or physical inconsistencies either across modalities or with common world knowledge. Inspired by this observation, we propose \textbf{C}onflict-\textbf{O}riented \textbf{RE}asoning (\textbf{CORE}) framework, an effective paradigm that learns to endows multimodal large language models (MLLMs) with explicit conflict-capturing capability. To this end, CORE first constructs the Conflict Attribution Corpus (CAC) with fine-grained annotations of conflict factors and sources, providing essential data support for subsequent conflict perception training. By performing conflict-oriented representation enhancement and reasoning based on CAC, CORE achieves robust and generalizable conflict detection, effectively and rapidly adapting to unseen manipulation types with a few samples or in even zero-shot settings. Extensive experiments demonstrate that CORE surpasses state-of-the-art models. The dataset and code are publicly available at https://github.com/shen8424/CORE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
