AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
Paper • 2404.07921 • Published • 3
Le Minh Quan
insomnia1102
·
AI & ML interests
None yet
Organizations
None yet
upvoted 4
papers 8 months ago
AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
Paper • 2410.22143 • Published • 1
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Paper • 2401.06373 • Published • 2
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
Paper • 2507.18546 • Published • 39