Research map / Adversarial robustness and security / Attacks on text and graphs
Membership Inference Attacks with False Discovery Rate Control
Chenxu Zhao, Wei Qian, Aobo Chen, Mengdi Huai
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add MIAFdR wrapper | classifier-based MIA · CIFAR-100 | attack accuracy: 76.81 -> 78.19 | Improved |
| add MIAFdR wrapper | classifier-based MIA · CIFAR-100 | AUROC: 84.35 -> 84.46 | No clear effect |
| add MIAFdR wrapper | classifier-based MIA · Tiny-ImageNet | attack accuracy: 69.67 -> 71.18 | Improved |
| add MIAFdR wrapper | classifier-based MIA · Tiny-ImageNet | AUROC: 76.99 -> 77.06 | No clear effect |
| add MIAFdR wrapper | classifier-based MIA · CIFAR-10 (7,000 test samples) | inference time: 137.84 s + 0.01 s | No clear effect |
| add MIAFdR wrapper | LiRA · CIFAR-10 | ROC curve TPR at low FPR | Improved |
| increase calibration set size (ablation) | metric-based MIAFdR · CIFAR-10 | attack accuracy | Improved |
| vary member to non-member ratio in evaluation set (ablation) | MIAFdR · CIFAR-10 | AUROC | No clear effect |
| apply knowledge distillation defense to target model (ablation) | MIAFdR · CIFAR-10 | FDR control | No clear effect |
Closest papers by meaning
- Causal Evaluation of Membership Inference Attacks (NeurIPS 2026 · similarity 0.87)
- Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration (NeurIPS 2024 · similarity 0.87)
- Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning (NeurIPS 2025 · similarity 0.86)
- Low-Cost High-Power Membership Inference Attacks (ICML 2024 · similarity 0.86)
- Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning (ICLR 2024 · similarity 0.86)
- DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
