Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang
Topics & Concepts
Computer scienceTroubleshootingMedicineIdentification (biology)Component (thermodynamics)EngineeringInterchangeabilityAutomationAction (physics)Pipeline (software)Multi-Agent Systems and NegotiationExplainable Artificial Intelligence (XAI)Topic Modeling