Open AccessImproving Robustness to Model Inversion Attacks via Mutual Information Regularization
Author(s) -
Tianhao Wang,
Yuheng Zhang,
Ruoxi Jia
Publication year - 2021
Publication title -
proceedings of the ... aaai conference on artificial intelligence
Language(s) - Uncategorized
Resource type - Journals
eISSN - 2374-3468
pISSN - 2159-5399
DOI - 10.1609/aaai.v35i13.17387
Subject(s) - computer science , adversary , heuristics , mutual information , machine learning , private information retrieval , artificial intelligence , robustness (evolution) , limiting , information leakage , regularization (linguistics) , data mining , computer security , engineering , gene , operating system , mechanical engineering , biochemistry , chemistry