Goto

Collaborating Authors

 Industry






WhenLLMMeetsDRL: AdvancingJailbreaking EfficiencyviaDRL-guidedSearch

Neural Information Processing Systems

These attacks either leverage in-contextlearning [6,35,66,28,5]orgenetic methods [65,27,32]. Specifically,in-contextlearning attacks keep querying another helper LLM togenerate and refine jailbreaking prompts. As shown in Section 4, purely relying on in-context learning has a limited ability tocontinuously refinetheprompts. Genetic method-based attacks design differentmutators that leverage the helper LLM to modify the jailbreaking prompts. They refine the prompts by iteratively selecting the promising prompts as the seeds for the next round.




How do birds stay warm in winter?

Popular Science

How do birds stay warm in winter? Puffing up is just the start. Breakthroughs, discoveries, and DIY tips sent six days a week. Then you notice a robin hopping from branch to branch. Nearby, ducks are calmly swimming in the pond and waddling around on the ice.