Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
Paper • 2410.18469 • Published • 1
weiwei yang
weiweiyang
·
AI & ML interests
None yet
Recent Activity
upvoted a collection about 21 hours ago
GridSFM authored a paper 2 days ago
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities authored a paper 2 days ago
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N SamplingOrganizations
authored 4
papers 2 days ago
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
Paper • 2601.22636 • Published • 22
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
Paper • 2602.06854 • Published • 6
Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models
Paper • 2312.09601 • Published