Membership-Invariant Subspace Training

doi:doi:10.57702/4f2ietq5

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

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

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