arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18880cs.CVcs.AI
收藏

FOCA:基于多模态大语言模型的频率导向跨域伪造检测、定位与解释

FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model

Harbin Institute of Technology(哈尔滨工业大学);DZ-Matrix;Guangdong Laboratory of Artificial Intelligence and Digital Economy(广东省人工智能与数字经济实验室);Chongqing Research Institute of HIT(哈尔滨工业大学重庆研究院);University of New South Wales(新南威尔士大学)

Zhou Liu, Tonghua Su, Hongshi Zhang, Fuxiang Yang, Donglin Di, Yang Song, Lei Fan

AI总结:

FOCA通过多模态大语言模型整合空间与频域特征,实现图像伪造的高精度检测、定位及可解释性解释,优于现有方法。

摘要:

图像篡改技术的进步,特别是生成模型,对媒体验证、数字取证和公众信任构成了重大挑战。现有图像伪造检测和定位(IFDL)方法存在两个关键局限:过度依赖语义内容而忽视纹理线索,以及对细微低层篡改痕迹的可解释性有限。为了解决这些问题,我们提出FOCA,一种基于多模态大语言模型的框架,通过交叉注意力融合模块整合来自RGB空间域和频域的判别特征。这种设计使能够准确检测和定位伪造,同时提供明确、可由人类解释的跨域解释。我们进一步引入FSE-Set,一个包含多样化真实和篡改图像、像素级掩码和双域标注的大型数据集。广泛实验表明,FOCA在空间域和频域的检测性能和可解释性上均优于现有最先进方法。

英文摘要:

Advances in image tampering techniques, particularly generative models, pose significant challenges to media verification, digital forensics, and public trust. Existing image forgery detection and localization (IFDL) methods suffer from two key limitations: over-reliance on semantic content while neglecting textural cues, and limited interpretability of subtle low-level tampering traces. To address these issues, we propose FOCA, a multimodal large language model-based framework that integrates discriminative features from both the RGB spatial and frequency domains via a cross-attention fusion module. This design enables accurate forgery detection and localization while providing explicit, human-interpretable cross-domain explanations. We further introduce FSE-Set, a large-scale dataset with diverse authentic and tampered images, pixel-level masks, and dual-domain annotations. Extensive experiments show that FOCA outperforms state-of-the-art methods in detection performance and interpretability across both spatial and frequency domains.

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。

↑