BadSAD：针对深度半监督异常检测的干净标签后门攻击
BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
AI总结：
本文提出 BadSAD 框架，通过触发器注入与潜在空间操纵两阶段方法，对 DeepSAD 深度半监督异常检测模型实施干净标签后门攻击，揭示了该类系统的安全风险。
摘要：
图像异常检测（IAD）在工业检测、医学成像和安全等应用中至关重要。尽管 DeepSAD（深度半监督异常检测）等深度学习模型取得了进展，但这些模型仍易受后门攻击，带来重大安全挑战。本文提出 BadSAD，一种专门针对 DeepSAD 模型的新型后门攻击框架。该方法包含两个关键阶段：触发器注入，即将细微触发器嵌入正常图像；潜在空间操纵，即将中毒图像定位并聚类在正常图像附近，使触发器显得无害。在基准数据集上的大量实验验证了该攻击策略的有效性，凸显了后门攻击对基于深度学习的异常检测系统造成的严重风险。
英文摘要：
Image anomaly detection (IAD) is essential in applications such as industrial inspection, medical imaging, and security. Despite the progress achieved with deep learning models like Deep Semi-Supervised Anomaly Detection (DeepSAD), these models remain susceptible to backdoor attacks, presenting significant security challenges. In this paper, we introduce BadSAD, a novel backdoor attack framework specifically designed to target DeepSAD models. Our approach involves two key phases: trigger injection, where subtle triggers are embedded into normal images, and latent space manipulation, which positions and clusters the poisoned images near normal images to make the triggers appear benign. Extensive experiments on benchmark datasets validate the effectiveness of our attack strategy, highlighting the severe risks that backdoor attacks pose to deep learning-based anomaly detection systems.
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。
