Research map / Adversarial robustness and security / Attacks on text and graphs
Amnesiac Machine Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Reverse parameter updates from batches containing sensitive records | Amnesiac Unlearning · CIFAR100 membership inference | recall: 0.97478991 -> 0.0 | Helped |
| Relabel sensitive examples with randomly selected incorrect labels and train for one epoch | Unlearning · CIFAR100 membership inference | recall: 0.97478991 -> 0.0 | Helped |
| Retrain without the sensitive records for one epoch | Naive Retraining · CIFAR100 membership inference | recall: 0.97478991 -> 0.09243697 | Helped |
| Retrain without the sensitive records for two epochs | Naive Retraining · CIFAR100 membership inference | recall: 0.97478991 -> 0.05882352 | Helped |
| Remove sensitive records from the dataset without changing the trained model | Naive Retraining · CIFAR100 membership inference, epoch 0' | recall: 0.97478991 -> 0.97478991 | No clear effect |
| Relabel sensitive examples before training on the modified dataset | Unlearning · CIFAR100 membership inference, epoch 0' | recall: 0.97478991 -> 0.97478991 | No clear effect |
| Remove no more than 1% of batches through amnesiac unlearning (ablation) | Amnesiac Unlearning · CIFAR100 | test accuracy | No clear effect |
| Remove a larger share of batches through amnesiac unlearning (ablation) | Amnesiac Unlearning · CIFAR100 | test accuracy | Hurt |
Closest papers by meaning
- Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable (NeurIPS 2024 · similarity 0.87)
- Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage (AAAI 2025 · similarity 0.86)
- Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models (NeurIPS 2024 · similarity 0.86)
- Certified Unlearning for Neural Networks (ICML 2025 · similarity 0.85)
- Rethinking Adversarial Robustness in the Context of the Right to be Forgotten (ICML 2024 · similarity 0.85)
- Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation (AAAI 2024 · 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.