Torsten Krauß

1. TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
   2025/06/09 by Torsten Krauß, Hamid Dashtbani, Krauß, Torsten +3 · 8 citations
   Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Advanced Malware Detection Techniques