DAMIA: Leveraging Domain Adaptation as a Defense against Membership Inference Attacks

no code implementations • 16 May 2020 • Hongwei Huang, Weiqi Luo, Guoqiang Zeng, Jian Weng, Yue Zhang, Anjia Yang

However, the DL models may be prone to the membership inference attack, where an attacker determines whether a given sample is from the training dataset.

Domain Adaptation Inference Attack +1