The speed and scale at which machine learning (ML) systems are deployed are
accelerating even as an increasing number of studies highlight their potential
for negative impact. There is a clear need for companies and regulators to
manage the risk from proposed ML systems before they har
本文提出了一种人工智能安全分类法，系统化地分类机器学习系统的威胁、漏洞和安全控制。首先分类了针对 ML 系统的攻击，定义了特定于 ML 的安全性并讨论其特点。然后，明确了所有相关资产和利益相关者，并为 ML 特定威胁提供了一般分类法。最后，通过对最近文献的广泛审查，收集了对 ML 特定威胁的各种安全控制措施，并将 ML 系统的漏洞和控制措施按照其整个生命周期中容易受到攻击的资源进行分类。