cs.CRNov 6, 2026

Cutpurse: Decomposing Explanation-Guided Model Extraction on Tabular Data

Authors: Seyma Selcan Magara, Hanru Zhang, Fatme El Zahraa Hamad, Nico Pfeifer, Mete Akgün

Organizations: University of Tübingen, Tübingen, Germany *Medical Data Privacy and Privacy-Preserving Machine Learning Group

Abstract

Explanation APIs are often treated as increasing model-extraction risk, but an end-to-end attack comparison cannot show whether an explanation reveals model-specific information or merely supplies a convenient next-query coordinate. We study this distinction for explanation-guided extraction of tabular classifiers. We separate an explanation into an attribution channel, which ranks influential features, and a coordinate channel, which supplies candidate feature values for perturbing those features. We then test whether the useful bin edges are privileged to the service or reproducible from the adversary's own data. Across six datasets and five target families, using attribution rankings to choose which features to perturb provides no systematic extraction advantage. Lime's discretization bin edges can improve fidelity by up to 41 percentage points on continuous features, but those edges are quantiles of the explainer's background data rather than properties of the target model. In controlled comparisons, an attacker-side grid reproduces the useful bin-edge gains without querying an explanation API. We use these findings to derive Cutpurse, which combines a self-computed grid with diverse query generation and boundary search. Against a service that withholds bin edges, Cutpurse improves fidelity by 16.3 percentage points on continuous-feature targets. It also exceeds the undefended published attack by 7.0 percentage points. Thus, withholding default Lime bin edges alone does not prevent effective extraction under the in-domain auxiliary-input, probability-output, and same-family surrogate assumptions studied here. Our results concern default Lime and Shap configurations for tabular classifiers. They do not establish the same conclusion for other explainers, target classes, or data-free attackers.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 12, 2026

When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers

Language model classifiers with explanations are used for moderation, routing, topic triage, and low-resource annotation. We study black-box auditing when the defender has only clean calibration data without trigger information but can ask the classifier for a label plus a short rationale or quoted evidence. We introduce Groundedness Drift, a lightweight score measuring whether the answer summary remains grounded in the input. Across two 7B backbones, five datasets, and four common non-adaptive OpenBackdoor-style attack families, Groundedness Drift achieves higher AUROC and lower residual target ASR than every compared detector in all cases at a nominal 5% clean-FPR budget. We then evaluate Unsupported Groundedness, a multi-probe escalation for explanation-camouflage stress cases. Unsupported Groundedness improves signals but does not close the adaptive gap.
May 15, 2026

AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark

Automated machine learning pipelines increasingly produce models whose predictions must be explained to end users, auditors, and downstream decision systems. The most widely used feature attribution methods (SHAP, Integrated Gradients, LIME) are typically chosen by convention rather than measured fidelity, because rigorous evaluation is impeded by the absence of ground-truth attribution on real data. We propose AGOP-IxG, a fast per-sample attribution method for tabular classifiers that pre-multiplies the per-sample gradient by a top-KK rank-truncated Average Gradient Outer Product matrix, and evaluate it against four widely-used baselines on a controlled tabular benchmark designed for AutoML practitioners. In Part 1, we construct three synthetic multi-class tabular tasks (linear, sparse nonlinear, interaction-based) where ground-truth attribution per sample is analytically or numerically derivable, and compare five methods: AGOP-IxG, SHAP (DeepExplainer), Integrated Gradients, InputXGradient, and LIME. AGOP-IxG leads on Spearman rank correlation and noise feature mass on all three synthetic datasets, and on top-kk precision on the interaction dataset. Across all settings, AGOP-IxG is approximately 350×350\times to 1,650×1{,}650\times faster than SHAP. In Part 2, we evaluate global faithfulness on Adult Income and Credit Card Default using the ROAR protocol; the methods cluster within ∼1.7%\sim 1.7\% relative AUC, consistent with AGOP-IxG being optimized for per-sample local attribution rather than global feature ranking.
May 28, 2026

Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?

Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. However, this transparency creates exploitable vulnerabilities for model extraction attacks. We present the first model extraction attack specifically designed for graph classification under strict black-box constraints where the attacker observes only discrete class labels and binary explanation masks (no probability scores, gradients, or confidence values). Our method (1) uses model explanation outputs to guide Monte Carlo edge sensitivity estimation toward decision boundaries, with Hoeffding concentration guarantees on estimation accuracy and (2) exploits explanation subgraphs to efficiently narrow the boundary search space. Extensive experiments on benchmark graph datasets across multiple domains demonstrate our method's superiority over comparable baselines. These findings demonstrate that such explainability interfaces create exploitable attack surfaces, informing both defensive mechanisms and policy frameworks for explainable AI mandates. The implementation code is provided in https://github.com/LabRAI/XSTEAL/.