wanghangpsu / MM-BDLinks
The implementation of the IEEE S&P 2024 paper MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic
☆13Updated last year
Alternatives and similar repositories for MM-BD
Users that are interested in MM-BD are comparing it to the libraries listed below
Sorting:
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆60Updated 9 months ago
- ☆27Updated last year
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 months ago
- ☆14Updated last year
- [ICML 2023] Official code implementation of "Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning (htt…☆42Updated last week
- A curated list of papers & resources on backdoor attacks and defenses in deep learning.☆219Updated last year
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning (Poster at NeurIPS 2023)☆36Updated this week
- ☆52Updated 2 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆128Updated 10 months ago
- Code related to the paper "Machine Unlearning of Features and Labels"☆71Updated last year
- ☆537Updated 2 months ago
- ☆14Updated last year
- A Pytroch Implementation of Some Backdoor Attack Algorithms, Including BadNets, SIG, FIBA, FTrojan ...☆20Updated 9 months ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆130Updated last year
- ☆33Updated last year
- Github Repo for AAAI 2023 paper: On the Vulnerability of Backdoor Defenses for Federated Learning☆40Updated 2 years ago
- A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)☆269Updated 8 months ago
- ☆24Updated last year
- ☆356Updated 2 months ago
- Code for the paper: Label-Only Membership Inference Attacks☆66Updated 4 years ago
- [Oakland 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆26Updated 5 months ago
- ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341☆73Updated 2 years ago
- ☆70Updated 3 years ago
- This is the source code for Data-free Backdoor. Our paper is accepted by the 32nd USENIX Security Symposium (USENIX Security 2023).☆31Updated last year
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆17Updated 6 years ago
- ☆25Updated last year
- Code for ML Doctor☆91Updated last year
- ☆32Updated 4 years ago
- ☆21Updated 3 years ago