2 matches found
backdoor-learning-resources
后门学习资源 本 Github 仓库总结了 后门学习(Backdoor Learning) 资源清单。更多细节和分类标准,请参考我们的综述。 我们将尽最大努力以月度为单位持续维护本 Github 仓库。 为什么是后门学习? 后门学习是一个新兴的研究领域,讨论机器学习算法训练过程中的安全问题。它在现实中安全地采用第三方训练资源或模型时至关重要。 注意:“后门”也常被称为“神经木马”或“木马”。 新闻 2023/7/24:我新增了十篇 ICLR'23 论文。该会议的所有论文现在应该都已收录。 2023/7/23:我新增了七篇 NeurIPS'22 论文和四篇 AAAI'23...
6AI score
SaveExploits0References92
Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
Vision Transformers ViTs have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we...
7.2AI score
SaveExploits0
20