Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

NeurIPS(2023)

引用 1|浏览43
暂无评分
摘要
Privacy-preserving instance encoding aims to encode raw data as feature vectors without revealing their privacy-sensitive information. When designed properly, these encodings can be used for downstream ML applications such as training and inference with limited privacy risk. However, the vast majority of existing instance encoding schemes are based on heuristics and their privacy-preserving properties are only validated empirically against a limited set of attacks. In this paper, we propose a theoretically-principled measure for the privacy of instance encoding based on Fisher information. We show that our privacy measure is intuitive, easily applicable, and can be used to bound the invertibility of encodings both theoretically and empirically.
更多
查看译文
关键词
instance encoding,information,privacy-preserving
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要