Sondej, Filip

1. Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems
   2025/02/26 by Pierre Peigne-Lefebvre, Mikołaj Kniejski, Peigne-Lefebvre, Pierre +11 · 14 citations
   Computer Science · Social Sciences · #Access Control and Trust #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multiagent Systems (cs.MA) #Security and Verification in Computing
2. How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis
   2024/11/10 by Yang, Yushi, Sondej, Filip, Mayne, Harry +2 · 2 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)