研究人员开发了一种名为Moat的动态分析方法，通过在模型生命周期中监控其与宿主系统的交互来确保机器学习模型执行的安全性。该方法以Re-Moat的形式实现，旨在检测传统静态扫描方法可能遗漏的嵌入在模型构件中的恶意行为。使用来自Hugging Face Hub的大型数据集和CVE概念验证进行的评估表明，Moat在以接近零的误报率检测各种攻击类别方面是有效的。 AI
影响 这项研究可能带来更强大的防御措施，以应对嵌入在ML模型中的新型攻击，从而提高AI部署的安全性。
排序理由 该集群包含一篇详细介绍ML模型安全新方法的论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.19023v1 Announce Type: cross Abstract: The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defen…
The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses. Current model-scanning solutions primarily re…
The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses. Current model-scanning solutions primarily re…