Pith. sign in

Label-only mem- bership inference attacks

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Membership Inference Attacks for Unseen Classes

cs.LG · 2025-06-06 · conditional · novelty 7.0

In a new 'unseen class' setting for membership inference, quantile regression attacks outperform shadow model attacks, which fall to the level of a global-threshold baseline.

citing papers explorer

Showing 1 of 1 citing paper.

  • Membership Inference Attacks for Unseen Classes cs.LG · 2025-06-06 · conditional · none · ref 4

    In a new 'unseen class' setting for membership inference, quantile regression attacks outperform shadow model attacks, which fall to the level of a global-threshold baseline.