uw-nsl / CleanGenLinks
[EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
☆15Updated 2 months ago
Alternatives and similar repositories for CleanGen
Users that are interested in CleanGen are comparing it to the libraries listed below
Sorting:
- ☆15Updated 2 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 9 months ago
- ☆21Updated last year
- ☆28Updated 7 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆37Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 10 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆57Updated 2 years ago
- Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"☆56Updated 7 months ago