Hamid Dashtbani

1. TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
   2025/06/09 by Torsten Krauß, Krauß, Torsten, Hamid Dashtbani +3 · 8 citations
   Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Advanced Malware Detection Techniques
2. Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
   2026/07/16 by Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh
   #cs.LG #cs.AI #cs.CR