facebookresearch / certified-removal
Certified Removal from Machine Learning Models
☆65Updated 3 years ago
Alternatives and similar repositories for certified-removal:
Users that are interested in certified-removal are comparing it to the libraries listed below
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆49Updated 2 years ago
- Code for Auditing DPSGD☆37Updated 3 years ago
- ☆31Updated 7 months ago
- code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22☆22Updated 3 years ago
- ☆56Updated 4 years ago
- Public implementation of ICML'19 paper "White-box vs Black-box: Bayes Optimal Strategies for Membership Inference"☆16Updated 4 years ago
- Membership Inference Attacks and Defenses in Neural Network Pruning☆28Updated 2 years ago
- ☆44Updated 8 months ago
- [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…☆67Updated last year
- Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)☆47Updated 2 years ago
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 6 years ago
- Code for the paper: Label-Only Membership Inference Attacks☆65Updated 3 years ago
- ☆34Updated last year
- ☆29Updated 10 months ago
- ☆25Updated 6 years ago
- ☆11Updated 2 years ago
- ☆19Updated 7 months ago
- R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]☆36Updated 2 years ago
- ☆12Updated last year
- The source code for ICML2021 paper When Does Data Augmentation Help With Membership Inference Attacks?☆8Updated 3 years ago
- Camouflage poisoning via machine unlearning☆17Updated 2 years ago
- ☆24Updated 3 years ago
- ☆26Updated 6 years ago
- ☆25Updated 2 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated last year
- Likelihood Ratio Attack (LiRA) in PyTorch☆14Updated last month
- ☆19Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆30Updated last year
- ☆29Updated 3 years ago