cs.LGNov 7, 2026

Bayesian Low-Rank Posteriors for Scalable Membership Inference

Authors: Khanh Nguyen, Antonio Emanuele Cinà, Andrey Barsky, Alejandra Reinares, Fabio Roli, Dimosthenis Karatzas

Organizations: Computer Vision Center, Universitat Autònoma de Barcelona · University of Trieste, MIGe, Italy · University of Genoa, DIBRIS, Italy · University of Cagliari, DIEE, Italy

Abstract

Membership inference attacks (MIAs) aim to determine whether a sample was used during the training of a target model. Strong MIAs rely on reference (or shadow) models to estimate target-conditional score distributions, but training such ensembles is computationally expensive for modern large-scale Vision--Language Models (VLMs). In this work, we propose a scalable alternative that replaces explicit reference-model training with a Bayesian approximation over low-rank adaptation parameters. Specifically, we model uncertainty only within the LoRA subspace and construct a posterior from a single training run, from which we sample a diverse set of virtual reference models. We instantiate this approach using Stochastic Weight Averaging Gaussian (SWAG), enabling efficient approximation of target-conditional score distributions at a fraction of the cost of conventional shadow-model ensembles. We evaluate the resulting attack on three downstream-adapted VLMs across two privacy-sensitive visual question answering tasks, namely Document VQA and Medical VQA. To isolate the effect of pretraining knowledge, we additionally introduce a controlled synthetic dataset. Our approach outperforms standard reference-based attacks while requiring only a single reference-model fine-tuning run, making membership inference more practical for large VLMs.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 12, 2026

COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration

Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude and membership-score direction using a loosely distribution-matched, known non-member reference set. We instantiate COMPASS using Renyi-normalized KL divergence and Renyi divergence, with max-k aggregation over the most informative image-logit positions. Across LLaVA v1.5-7B, MiniGPT-4, and HuluMed-32B, spanning pretraining, instruction-tuning, and medical-image datasets, COMPASS outperforms baselines. On general-domain data, COMPASS achieves AUCs up to 0.88. On the distribution-matched medical evaluation, it reaches 0.64 AUC, while the strongest baseline remains at chance level. These results establish full-range adaptive perturbation analysis as an effective approach to VLLM membership inference.
Jun 16, 2026

CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models

Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties. Although several attempts have been made to evaluate MIAs on language models, the extant literature has suffered numerous difficulties in constructing clean evaluations to test new techniques. In particular, subtle distribution shifts between member and non-member sets can undermine the statistical validity of MIAs; recent work has underscored this by showing that "blind" methods with no access to the underlying model can perform far better than published methods on the same benchmarks. This paper constructs a benchmark for principled evaluation of MIAs against LLMs, by leveraging the insight that training data before and after a fixed point during training are drawn from the same distribution. Therefore, all open-source models with intermediate checkpoints and public training data can be converted into MIA testbeds. We apply our framework to a half-dozen published attacks on the Pythia and OLMo family of models, from 70M to 7B parameters. To facilitate further privacy research, we open-source a modular library for designing and implementing attacks in this setting: https://github.com/safr-ai-lab/pandora_llm.
Oct 22, 2025

Estimating Model-Level Membership Inference Vulnerability Without Reference Models

Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attacks require training numerous, often computationally expensive, reference models, limiting their practicality. We present a novel approach for estimating model-level vulnerability to the Likelihood Ratio Attack (LiRA), the strongest available attack, directly from the train and test loss distributions of the target model and without training any reference models. We show that LiRA's per-sample signal decomposes into a variance-ratio term and a residual mean-shift term, with the relative contribution of each determined by how much training collapses model uncertainty at the trained sample. This places models on a continuum, with different regimes calling for different reference-free loss-based statistics as proxies for LiRA TPR. The shapes of the loss distributions themselves indicate which proxy applies. We instantiate the framework with two natural proxies. At the heavy-tailed end, the LOSS attack TNR predicts LiRA TPR@FPR=10−310^{-3} with RMSE 0.036 across 10 image classification architectures and 4 datasets, outperforming low-cost reference-model attacks such as RMIA. At the symmetric end, the LOSS attack AUC predicts LiRA TPR with RMSE 0.018 across five GPT-2 sizes from 10M to 1B parameters.