REVIEW 1 cited by
Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
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
Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
read the original abstract
Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model. Previous Weight regularizations (e.g., L1 regularization) typically impose uniform penalties on all parameters, leading to a suboptimal tradeoff between model utility and privacy. In this work, we first show that only a small fraction of parameters substantially impact the privacy risk. In light of this, we propose Privacy-aware Sparsity Tuning (PAST), a simple fix to the L1 Regularization, by employing adaptive penalties to different parameters. Our key idea behind PAST is to promote sparsity in parameters that significantly contribute to privacy leakage. In particular, we construct the adaptive weight for each parameter based on its privacy sensitivity, i.e., the gradient of the loss gap with respect to the parameter. Using PAST, the network shrinks the loss gap between members and non-members, leading to strong resistance to privacy attacks. Extensive experiments demonstrate the superiority of PAST, achieving a state-of-the-art balance in the privacy-utility trade-off.
Forward citations
Cited by 1 Pith paper
-
Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
ProjRes achieves near-100% accuracy in membership inference on FedLLMs by measuring projection residuals of hidden embeddings on gradient subspaces, outperforming prior methods by up to 75.75% even under differential privacy.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.