Privacy Risks of Securing Machine Learning Models against Adversarial Examples
This work highlights a critical privacy-security trade-off for machine learning practitioners, showing that improving model robustness may compromise data privacy.
The paper investigates whether adversarial defense methods, designed to protect machine learning models from adversarial examples, inadvertently increase vulnerability to membership inference attacks, finding that these defenses can indeed elevate such risks compared to undefended models.
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security domain and the privacy domain have typically been considered separately. It is thus unclear whether the defense methods in one domain will have any unexpected impact on the other domain. In this paper, we take a step towards resolving this limitation by combining the two domains. In particular, we measure the success of membership inference attacks against six state-of-the-art defense methods that mitigate the risk of adversarial examples (i.e., evasion attacks). Membership inference attacks determine whether or not an individual data record has been part of a model's training set. The accuracy of such attacks reflects the information leakage of training algorithms about individual members of the training set. Adversarial defense methods against adversarial examples influence the model's decision boundaries such that model predictions remain unchanged for a small area around each input. However, this objective is optimized on training data. Thus, individual data records in the training set have a significant influence on robust models. This makes the models more vulnerable to inference attacks. To perform the membership inference attacks, we leverage the existing inference methods that exploit model predictions. We also propose two new inference methods that exploit structural properties of robust models on adversarially perturbed data. Our experimental evaluation demonstrates that compared with the natural training (undefended) approach, adversarial defense methods can indeed increase the target model's risk against membership inference attacks.