Pith. sign in

Membership Inference Attacks Against Machine Learning Models,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

method 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

ACCEPT 1

roles

method 1

polarities

use method 1

representative citing papers

Hyperparameters in Score-Based Membership Inference Attacks

cs.LG · 2025-02-10 · accept · novelty 6.0

A new shadow-model hyperparameter selection method (KL-LiRA) makes membership inference attacks nearly as effective without knowing target hyperparameters, and training-data-based hyperparameter tuning shows no detectable extra MIA leak under DP.

citing papers explorer

Showing 1 of 1 citing paper.

  • Hyperparameters in Score-Based Membership Inference Attacks cs.LG · 2025-02-10 · accept · none · ref 1

    A new shadow-model hyperparameter selection method (KL-LiRA) makes membership inference attacks nearly as effective without knowing target hyperparameters, and training-data-based hyperparameter tuning shows no detectable extra MIA leak under DP.