Research map / Adversarial robustness and security / Attacks on text and graphs
On the Importance of Difficulty Calibration in Membership Inference Attacks
Lauren Watson, Chuan Guo, Graham Cormode, Alexandre Sablayrolles
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 |
|---|---|---|---|
| Apply difficulty calibration to Loss | Score-based membership inference attacks · Credit, Adult, MNIST, CIFAR10, CIFAR100, ImageNet | AUC: 0.542 -> 0.648; 0.516 -> 0.554; 0.505 -> 0.519; 0.676 -> 0.731; 0.911 -> 0.903; 0.547 -> 0.557 | Mixed |
| Apply difficulty calibration to Gradient Norm | Score-based membership inference attacks · Credit, Adult, MNIST, CIFAR10, CIFAR100, ImageNet | AUC: 0.513 -> 0.579; 0.510 -> 0.523; 0.504 -> 0.514; 0.678 -> 0.787; 0.912 -> 0.924; 0.540 -> 0.511 | Mixed |
| Apply difficulty calibration to Confidence | Score-based membership inference attacks · Credit, Adult, MNIST, CIFAR10, CIFAR100, ImageNet | AUC: 0.501 -> 0.553; 0.507 -> 0.510; 0.503 -> 0.510; 0.629 -> 0.635; 0.852 -> 0.707; 0.544 -> 0.515 | Mixed |
| Use difficulty-calibrated scores instead of original scores | Score-based membership inference attacks · Membership inference at low recall | precision | Improved |
| Use difficulty calibration | Score-based membership inference attacks · Skewed member:non-member ratios | precision | Improved |
Closest papers by meaning
- Low-Cost High-Power Membership Inference Attacks (ICML 2024 · similarity 0.88)
- Confidence Is All You Need for MI Attacks (Student Abstract) (AAAI 2024 · similarity 0.88)
- Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning (ICLR 2024 · similarity 0.87)
- Estimating Model-Level Membership Inference Vulnerability Without Reference Models (NeurIPS 2026 · similarity 0.86)
- Exploring the limits of strong membership inference attacks on large language models (NeurIPS 2025 · similarity 0.86)
- What Really is a Member? Discrediting Membership Inference via Poisoning (NeurIPS 2025 · similarity 0.86)
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.
