MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training.

Jiacheng Li Ninghui Li 0001 Bruno Ribeiro 0001 MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training. 2024 USENIX Security Symposium https://www.usenix.org/conference/usenixsecurity24/presentation/li-jiacheng conf/uss/2024 db/conf/uss/uss2024.html#LiL024