XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks
Factual evidence
What the source reports
Researchers demonstrate XposedMIA, using LIME explainability outputs to execute one-shot membership inference attacks on ML models.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 11 November 2026
- Collected by OneBench
- 12 Nov 2026, 02:02 UK
Stored source excerpt
arXiv:2611.12067v2 Announce Type: replace Abstract: Machine learning (ML) services increasingly expose explainability outputs alongside model predictions. While such explanations are intended to improve transparency, they…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Exposing local explanations like LIME creates a new privacy attack vector that can extract sensitive training data from production models.
Do what
Review explainable AI deployments with model risk and security teams to assess vulnerability to membership inference attacks.