Leveraging Domain Adaptation as a Defense Against Membership Inference Attacks
Hongwei Huang, Weiqi Luo, Guoqiang Zeng, Jian Weng, Yue Zhang, Anjia Yang
Abstract
Deep Learning (DL) techniques allow ones to train models from a dataset to solve tasks. DL has attracted much interest given its fancy performance and potential market value, while security issues are amongst the most colossal concerns. 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. Efforts have been made to hinder the attack but unfortunately, they may lead to a major overhead or impaired usability. In this article, we propose and implement DAMIA, leveraging Domain Adaptation (DA) as a defense aginist membership inference attacks. Our observation is that during the training process, DA obfuscates the dataset to be protected using another relate and similar dataset, and derives a model that underlyingly extracts the features from both datasets. Seeing that the model is obfuscated, membership inference fails, while the extracted features provide supports for usability. Extensive experiments have been conducted to validates our intuition. The model trained by DAMIA has a negligible footprint to the usability and introduces slight overhead compared with other defenses. Our experiment also excludes factors that may hinder the performance of DAMIA, and comparisons with other defenses, providing a potential guideline to vendors and researchers to benefit from our solution in a timely manner.