作者位次 #2/7ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
Julia Bazinska · Max Mathys · Francesco Casucci · Mateo Rojas-Carulla · Xander Davies · Alexandra Souly · Niklas Pfister