DisPatch：基于扩散模型的物体检测对抗性补丁消除方法
DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models
AI总结：
本文提出DisPatch，一种基于扩散模型的物体检测防御框架，通过再生和修正策略消除对抗性补丁，有效提升检测鲁棒性，实验表明其在隐藏攻击和生成攻击中均表现优异。
摘要：
物体检测在安全监控和视频分析等实际应用中至关重要。尽管最先进的检测器已取得进展，但仍易受对抗性补丁攻击影响，这些攻击可轻易应用于现实物体以隐藏真实物品或生成虚假物品，造成严重后果。本文提出DisPatch，首个基于扩散模型的物体检测防御框架。与以往旨在“检测并移除”对抗性补丁的方法不同，DisPatch采用“再生并修正”策略，利用生成模型消除攻击影响并保持输入图像完整性。具体而言，利用扩散模型的分布内生成能力再生整个图像，使其与良性数据对齐。随后通过修正过程识别并替换对抗区域为再生的良性替代物。DisPatch具有攻击无关性，无需事先了解现有补丁。在多个检测器上的广泛实验表明，DisPatch在隐藏攻击和生成攻击上均优于现有防御方法，实现隐藏攻击的最佳mAP@0.5得分为89.3%，将未定向生成攻击的成功率降至24.8%。此外，它在有效性与效率之间取得平衡，并保持对自适应攻击的强鲁棒性，使其成为一种实用且可靠的防御方法。
英文摘要：
Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch attacks, which can be easily applied to real-world objects to either conceal actual items or create non-existent ones, leading to severe consequences. In this work, we introduce DisPatch, the first diffusion-based defense framework for object detection. Unlike previous works that aim to "detect and remove" adversarial patches, DisPatch adopts a "regenerate and rectify" strategy, leveraging generative models to disarm attack effects while preserving the integrity of the input image. Specifically, we utilize the in-distribution generative power of diffusion models to regenerate the entire image, aligning it with benign data. A rectification process is then employed to identify and replace adversarial regions with their regenerated benign counterparts. DisPatch is attack-agnostic and requires no prior knowledge of the existing patches. Extensive experiments across multiple detectors demonstrate that DisPatch consistently outperforms state-of-the-art defenses on both hiding attacks and creating attacks, achieving the best overall mAP@0.5 score of 89.3% on hiding attacks, and lowering the attack success rate to 24.8% on untargeted creating attacks. Moreover, it strikes the balance between effectiveness and efficiency, and maintains strong robustness against adaptive attacks, making it a practical and reliable defense method.
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。
