arxiv:2411.07133
Fengqing Jiang
fqjiang
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware
Decoding
upvoted
a
paper
2 days ago
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
upvoted
a
paper
2 days ago
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Organizations
models
None public yet
datasets
None public yet