ResearchTrend.AI
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts

TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts

T. Krauß
Hamid Dashtbani
Alexandra Dmitrienko
ArXiv (abs)PDFHTML

Papers citing "TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts"

Title
No papers