TASI-LAB / Unlearning-inversion-attacks
This repository contains Python code for the paper "Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning".
☆14Updated last year
Alternatives and similar repositories for Unlearning-inversion-attacks:
Users that are interested in Unlearning-inversion-attacks are comparing it to the libraries listed below
- ☆27Updated 3 years ago
- ☆42Updated last year
- Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)☆46Updated 2 years ago
- [ICML 2023] Official code implementation of "Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning (htt…☆39Updated 3 months ago
- Code for the paper: Label-Only Membership Inference Attacks☆64Updated 3 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆121Updated 4 months ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated last year
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆70Updated 6 years ago
- ☆27Updated last year
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆54Updated 2 years ago
- ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341☆70Updated 2 years ago
- Code related to the paper "Machine Unlearning of Features and Labels"☆69Updated last year
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 years ago
- ☆69Updated 2 years ago
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆17Updated 5 years ago
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆53Updated 3 months ago
- Github Repo for AAAI 2023 paper: On the Vulnerability of Backdoor Defenses for Federated Learning☆37Updated 2 years ago
- ☆25Updated 2 years ago
- Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)☆46Updated 5 years ago
- ☆14Updated 9 months ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆31Updated 3 years ago
- ☆48Updated last year
- Invisible Backdoor Attack with Sample-Specific Triggers☆94Updated 2 years ago
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆30Updated 3 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆48Updated 6 years ago
- ☆19Updated 6 months ago
- ☆21Updated last year
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning (Poster at NeurIPS 2023)☆36Updated last year
- [ICLR2024] "Backdoor Federated Learning by Poisoning Backdoor-Critical Layers"