cleverhans-lab / unrolling-sgdLinks
code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22
☆22Updated 3 years ago
Alternatives and similar repositories for unrolling-sgd
Users that are interested in unrolling-sgd are comparing it to the libraries listed below
Sorting:
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆50Updated 2 years ago
- Camouflage poisoning via machine unlearning☆17Updated last week
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- ☆25Updated 3 years ago
- Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)☆48Updated 3 years ago
- ☆31Updated 9 months ago
- ☆24Updated 2 years ago
- ☆44Updated 10 months ago
- Membership Inference Attacks and Defenses in Neural Network Pruning☆28Updated 2 years ago
- ☆20Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 7 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Updated 2 years ago
- Certified Removal from Machine Learning Models☆66Updated 3 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆19Updated 2 years ago
- ☆33Updated last year
- [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…☆71Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆58Updated 2 years ago
- ☆19Updated 9 months ago
- Code for the paper: Label-Only Membership Inference Attacks☆65Updated 3 years ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆34Updated 5 years ago
- Code related to the paper "Machine Unlearning of Features and Labels"☆70Updated last year
- Anti-Backdoor learning (NeurIPS 2021)☆81Updated last year
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆37Updated 9 months ago
- Code for Backdoor Attacks Against Dataset Distillation☆35Updated 2 years ago
- [CVPRW'22] A privacy attack that exploits Adversarial Training models to compromise the privacy of Federated Learning systems.☆11Updated 2 years ago
- ☆19Updated 4 years ago
- ☆23Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆11Updated 2 years ago
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆21Updated 5 years ago