增强目标检测鲁棒性：在对抗性补丁攻击存在的情况下检测并恢复置信度
Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks
AI总结：
本研究针对YOLOv5目标检测模型面临的对抗性补丁攻击，提出结合EigenCAM与网格搜索优化补丁放置，并评估了SAC、Inpainting和潜在扩散模型三种防御方法。结果表明，潜在扩散模型能显著恢复并超越原始检测置信度，展现出最佳的防御效果。
摘要：
计算机视觉系统的广泛应用凸显了其易受对抗性攻击的脆弱性，尤其是针对目标检测器的对抗性补丁攻击。本研究评估了YOLOv5模型抵御此类攻击的防御机制。通过应用EigenCAM和网格搜索来确定最佳放置位置，生成并放置了优化后的对抗性补丁。我们测试了多种防御方法，包括Segment and Complete (SAC)、Inpainting和Latent Diffusion Models。我们的流程包含三个主要阶段：补丁应用、目标检测和防御分析。结果表明，对抗性补丁使平均检测置信度降低了22.06%。防御方法恢复了置信度水平：SAC为3.45%，Inpainting为5.05%，而使用Latent Diffusion Model则显著提升了26.61%，甚至超过了原始准确率水平，凸显了其在缓解对抗性补丁影响方面的卓越有效性。
英文摘要：
The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against such attacks. Optimized adversarial patches were generated and placed in sensitive image regions, by applying EigenCAM and grid search to determine optimal placement. We tested several defenses, including Segment and Complete (SAC), Inpainting, and Latent Diffusion Models. Our pipeline comprises three main stages: patch application, object detection, and defense analysis. Results indicate that adversarial patches reduce average detection confidence by 22.06\%. Defenses restored confidence levels by 3.45\% (SAC), 5.05\% (Inpainting), and significantly improved them by 26.61\%, which even exceeds the original accuracy levels, when using the Latent Diffusion Model, highlighting its superior effectiveness in mitigating the effects of adversarial patches.
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。
