cs.LGNov 9, 2026

XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks

Authors: Omar Hamdache, Serdar Kara, Kıvanç Kuzey Dikici, Abdullah Çağlar Öksüz, Anisa Halimi, Erman Ayday, Sinem Sav

Organizations: Bilkent University, Ankara, Turkey · Case Western Reserve University, Cleveland, Ohio, USA · IBM Research, Dublin, Ireland

Abstract

Machine learning (ML) services increasingly expose explainability outputs alongside model predictions. While such explanations are intended to improve transparency, they may also reveal information about the underlying training data. In this work, we show that the local surrogate geometry employed by Local Interpretable Model-agnostic Explanations (LIME) can be repurposed as a proxy for a sample's distance to the model's decision boundary. We extend this boundary-distance view to tabular counterfactual explanations and, for the first time, to visual counterfactual explanations for image classifiers. We present XposedMIA, a one-shot, explanation-based black-box membership inference attack (MIA) framework that converts the returned explanation into a proxy for the queried sample's distance to the model decision boundary. After a one-time calibration step on a small labeled calibration set of as few as 30 samples, our attack requires only a single query for each target sample. Unlike prior label-only attacks requiring iterative queries or shadow training, our method relies solely on the predicted label and its accompanying explanation. Our evaluation indicates that XposedMIA achieves high effectiveness, with success rates of up to 0.95 using only a single query per target, revealing that releasing explanations introduces an additional channel for membership leakage.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Feb 21, 2026

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

Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a data point was used during training. Existing MIAs often assume access to public datasets, shadow models, confidence scores or the training distribution, which makes them vulnerable to defenses like confidence masking. Label-only MIAs avoid these assumptions but require thousands of queries per sample. We propose a cost-effective label-only MIA framework based on transferability and model extraction. Querying the target MM with active sampling, perturbation-based selection and synthetic data, we extract a surrogate SS on which membership inference is performed offline. This shifts query overhead to a one-time extraction phase. It also removes the restriction that defines the label-only setting: the attacker controls SS and can read its posteriors and training trajectory, so attacks that cannot be run against MM can be run against SS. On Location, Purchase and Texas, the strongest attack on SS improves AUC over the direct attack on MM by 0.90.9, 5.65.6 and 5.05.0 percentage points, and improves the true positive rate at 1%1\% false positive rate by 2.8×2.8\times to 6.3×6.3\times. We characterize how leakage transfer depends on surrogate fidelity, evaluate standard defenses, and report preliminary results on image datasets.
Sep 9, 2026

SoK: Privacy Attacks on Machine Learning via Explainable AI

Machine learning explanations reveal model behavior beyond predictions, creating attack surfaces for model confidentiality and data privacy. We systematize 25 studies that exploit explanations for model extraction, membership inference, and model inversion, treating attribute inference as partial inversion. Existing work is often labeled only black- or white-box, obscuring substantial differences in what explanation signal reaches an adversary. We therefore separate model knowledge from explanation acquisition and identify five paths: target-released, attacker-derived, secondary disclosure, privileged access, and released global artifacts. Across these paths, explanations reduce extraction cost, expose membership signals through explanation statistics, recourse distance, and explanation-guided robustness, and support spatial or algebraic reconstruction of private inputs. We compare system and threat models, explanation signals, auxiliary knowledge, target models, modalities, query budgets, evaluation metrics, reported performance, and defenses. Our analysis shows that no explanation family is uniformly unsafe and no defense is uniformly effective. Risk depends on which signal is exposed, how it is acquired, which asset is targeted, and what the attacker already knows. We argue that explanation privacy should therefore be evaluated as an end-to-end disclosure problem, with defenses matched to the acquisition path and protected asset.
Mar 19, 2026

Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential information leakage associated with machine learning systems. Designing effective MIAs is a challenging task that usually requires extensive manual exploration of model behaviors to identify potential vulnerabilities. In this paper, we introduce AutoMIA -- a novel framework that leverages large language model (LLM) agents to automate the design and implementation of new MIA signal computations. By utilizing LLM agents, we can systematically explore a vast space of potential attack strategies, enabling the discovery of novel strategies. Our experiments demonstrate AutoMIA can successfully discover new MIAs that are specifically tailored to user-configured target model and dataset, resulting in improvements of up to 0.18 in absolute AUC over existing MIAs. This work provides the first demonstration that LLM agents can serve as an effective and scalable paradigm for designing and implementing MIAs with SOTA performance, opening up new avenues for future exploration.