facebookresearch / calibration_membershipLinks
Public implementation of the paper "On the Importance of Difficulty Calibration in Membership Inference Attacks".
☆16Updated 4 years ago
Alternatives and similar repositories for calibration_membership
Users that are interested in calibration_membership are comparing it to the libraries listed below
Sorting:
- ☆19Updated 2 years ago
- ☆20Updated last month
- ☆21Updated last year
- Code for the paper: Label-Only Membership Inference Attacks☆67Updated 4 years ago
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆48Updated 3 years ago
- ☆24Updated 3 years ago
- Membership Inference Attacks and Defenses in Neural Network Pruning☆28Updated 3 years ago
- Code for the paper "Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction" …☆12Updated 2 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Updated 5 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 3 years ago
- ☆32Updated last year
- Camouflage poisoning via machine unlearning☆18Updated 5 months ago
- Pytorch implementation of backdoor unlearning.☆21Updated 3 years ago
- verifying machine unlearning by backdooring☆20Updated 2 years ago
- Code for Backdoor Attacks Against Dataset Distillation☆35Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated 2 years ago
- Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)☆50Updated 3 years ago
- ☆26Updated 4 years ago
- ☆46Updated 6 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆27Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆36Updated last month
- ☆13Updated last year
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆20Updated 2 years ago
- A Fine-grained Differentially Private Federated Learning against Leakage from Gradients☆15Updated 2 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- ☆19Updated 4 years ago
- ☆13Updated 4 years ago
- Code for ML Doctor☆92Updated last year
- Anti-Backdoor learning (NeurIPS 2021)☆83Updated 2 years ago
- Code related to the paper "Machine Unlearning of Features and Labels"☆72Updated last year