Stolen Risks of Models with Security Properties
Yue Qin, Zhuoqun Fu, Chuyun Deng, Xiaojing Liao, Jia Zhang, Haixin Duan · 2023
Verifiable robust machine learning, as a new trend of ML security defense, enforces security properties (e.g., Lipschitzness, Monotonicity) on machine learning models and achieves satisfying accuracy-security trade-off. Such security properties identify a series of evasion strategies of ML security attackers and specify logical constraints on their effects on a classifier (e.g., the classifier is monotonically increasing along some feature dimensions). However, little has been done so far to understand the side effect of those security properties on the model privacy.