You're currently viewing an old version of this dataset. To see the current version, click here.

Membership-Invariant Subspace Training

Membership-Invariant Subspace Training (MIST) is a method for training classifiers that acts as a defense designed to specifically defend against black-box membership inference attacks on the most vulnerable instances in the training data.

Data and Resources

Cite this as

Jiacheng Li, Ninghui Li, Bruno Ribeiro (2025). Dataset: Membership-Invariant Subspace Training. https://doi.org/10.57702/4f2ietq5

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2311.00919
Author Jiacheng Li
More Authors
Ninghui Li
Bruno Ribeiro