Machine learning and deep learning algorithms are increasingly considered as potential candidates to perform black box side-channel security evaluations. Inspired by the literature on machine learning security, we put forward that it is easy to conceive implementations for which such black box security evaluations will incorrectly conclude that recovering the key is difficult, while an informed evaluator / adversary will reach the opposite conclusion (i.e., that the device is insecure given the amount of measurements available).

中文翻译：

---

如何愚弄基于黑盒机器学习的侧边通道安全性评估

机器学习和深度学习算法越来越被视为执行黑匣子边信道安全性评估的潜在候选者。受有关机器学习安全性的文献的启发，我们提出了一种容易想到的实现方案，对于这种实现方案，此类黑匣子安全性评估将错误地得出结论：很难恢复密钥，而知情的评估者/对手将得出相反的结论（即，鉴于可用的测量数量，该设备是不安全的）。