meng-wenlong / LMSanitator
☆20Updated last year
Alternatives and similar repositories for LMSanitator:
Users that are interested in LMSanitator are comparing it to the libraries listed below
- Composite Backdoor Attacks Against Large Language Models☆12Updated 11 months ago
- ☆20Updated 6 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 7 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆35Updated last year
- A toolbox for backdoor attacks.☆21Updated 2 years ago
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆30Updated 4 months ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- ☆19Updated 2 years ago
- ☆25Updated 5 months ago
- ☆24Updated 2 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated last year
- 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
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆15Updated 2 months ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆41Updated 2 years ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆30Updated 7 months ago
- ☆26Updated 2 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 4 months ago
- ☆13Updated 3 years ago
- [ICLR2024] "Backdoor Federated Learning by Poisoning Backdoor-Critical Layers"☆30Updated 3 months ago
- ☆20Updated 9 months ago
- Camouflage poisoning via machine unlearning☆17Updated 2 years ago
- ☆14Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆14Updated last year
- Pytorch implementation of backdoor unlearning.☆18Updated 2 years ago
- MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks…☆19Updated 6 months ago
- ☆42Updated 2 months ago
- ☆13Updated last year
- ☆30Updated 3 years ago