UCSB-NLP-Chang/SemanticSmooth
Implementation of paper 'Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing'
PythonMIT
Issues
- 0
emsemble_policy
#3 opened by huifeng3 - 2
Issues with running code
#1 opened by yewang - 2
Attack String Length for GCG
#2 opened by SinHanYang