Privacy Leakage Avoidance with Switching Ensembles.
MILCOM(2021)
摘要
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. Several approaches have been developed to mitigate this privacy leakage but the tradeoff performance implications of these defensive mechanisms (i.e., accuracy and utility of the defended machine learning model) are not well studied yet. We propose a novel approach of privacy leakage avoidance with switching ensembles (PASE), which both protects against current membership inference attacks and does that with very small accuracy penalty, while requiring acceptable increase in training and inference time. We test our PASE method, along with the the current state-of-the-art PATE approach, on three calibration image datasets and analyze their tradeoffs.
更多查看译文
关键词
privacy leakage avoidance,switching ensembles,PASE,current membership inference attacks,accuracy penalty,inference time,current state-of-the-art PATE approach,insignificantly reduced training sizes,insignificantly reduced accuracy,main privacy issues,recently developed attacks,random guess,attacked machine learning model,tradeoff performance implications,defended machine learning model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络