Papers
arXiv:2508.01268

Win-k: Improved Membership Inference Attacks on Small Language Models

Published on Aug 2
Authors:
,
,

Abstract

A new membership inference attack, win-k, is proposed and evaluated on small language models, demonstrating superior performance compared to existing attacks.

AI-generated summary

Small language models (SLMs) are increasingly valued for their efficiency and deployability in resource-constrained environments, making them useful for on-device, privacy-sensitive, and edge computing applications. On the other hand, membership inference attacks (MIAs), which aim to determine whether a given sample was used in a model's training, are an important threat with serious privacy and intellectual property implications. In this paper, we study MIAs on SLMs. Although MIAs were shown to be effective on large language models (LLMs), they are relatively less studied on emerging SLMs, and furthermore, their effectiveness decreases as models get smaller. Motivated by this finding, we propose a new MIA called win-k, which builds on top of a state-of-the-art attack (min-k). We experimentally evaluate win-k by comparing it with five existing MIAs using three datasets and eight SLMs. Results show that win-k outperforms existing MIAs in terms of AUROC, TPR @ 1% FPR, and FPR @ 99% TPR metrics, especially on smaller models.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.01268 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.01268 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.01268 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.