Matteo Prandi

1. Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
   Rewriting harmful requests as poetry bypassed safety filters across 25 LLMs, up to 18x the prose baseline rate.
   2025/11/19 by Piercosma Bisconti, Matteo Prandi, Bisconti, Piercosma +18 · 134 voices · 2 citations
   Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Topic Modeling #cs.AI #cs.CL
2. Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
   2026/07/24 by Marcantonio Bracale Syrnicov, Federico Pierucci, Matteo Prandi +4
   #cs.MA