XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks
cs.LG
Submitted: 2026-11-09
Updated: 2026-11-10
Code: https://github.com/privacytrustlab/datasets2http:
Terminology
Sources
- Model extraction from counterfactual explanations
- Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense
- Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach
- LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
- SmoothGrad: removing noise by adding noise
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis