REVIEW 2 cited by
Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We demonstrate how a target model's generalization gap leads directly to an effective deterministic black box membership inference attack (MIA). This provides an upper bound on how secure a model can be to MIA based on a simple metric. Moreover, this attack is shown to be optimal in the expected sense given access to only certain likely obtainable metrics regarding the network's training and performance. Experimentally, this attack is shown to be comparable in accuracy to state-of-art MIAs in many cases.
Forward citations
Cited by 2 Pith papers
-
A Unified Perspective on Adversarial Membership Manipulation in Vision Models
Adversarial perturbations reliably fabricate membership signals in vision-model MIAs, separated by a gradient-norm collapse trajectory that enables robust detection and inference.
-
Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
A bilevel optimization framework with curvature-guided geodesic perturbation reduces membership inference attack success while preserving downstream classification accuracy and sample quality.
Discussion (0). Sign in to comment.