LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings

TL;DR

This paper introduces LoMime, a cost-effective label-only membership inference attack that uses model extraction to significantly reduce query costs while maintaining high accuracy, even under strict black-box constraints.

Contribution

LoMime presents a novel transferability-based framework that shifts query overhead to a one-time model extraction phase, enabling efficient membership inference in label-only settings.

Findings

Achieves membership inference accuracy within ±1% of the target model.

Reduces query costs to about 1% of training samples.

Maintains effectiveness against standard defenses.

Abstract

Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training. Existing MIAs often rely on impractical assumptions such as access to public datasets, shadow models, confidence scores, or training data distribution knowledge and making them vulnerable to defenses like confidence masking and adversarial regularization. Label-only MIAs, even under strict constraints suffer from high query requirements per sample. We propose a cost-effective label-only MIA framework based on transferability and model extraction. By querying the target model M using active sampling, perturbation-based selection, and synthetic data, we extract a functionally similar surrogate S on which membership inference is performed. This shifts query overhead to a one-time extraction phase, eliminating repeated queries to M . Operating under strict black-box constraints, our method matches the performance of state-of-the-art label-only MIAs while significantly reducing query costs. On benchmarks including Purchase, Location, and Texas Hospital, we show that a query budget equivalent to testing $\approx1\%$ of training samples suffices to extract S and achieve membership inference accuracy within $\pm1\%$ of M . We also evaluate the effectiveness of standard defenses proposed for label-only MIAs against our attack.