BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents.
Yifei WangDizhan XueShengjie ZhangShengsheng QianPublished in: CoRR (2024)
Keyphrases
- multi agent systems
- multi agent
- multiple agents
- intelligent agents
- multiagent systems
- autonomous agents
- software agents
- cooperative
- artificial agents
- dynamic environments
- agent systems
- decision theoretic
- multi agent planning
- agent architecture
- agent behavior
- interacting agents
- agent based simulation
- game theoretic
- single agent
- action selection
- incomplete information
- resource allocation
- mobile agents
- reasoning process
- learning algorithm
- social welfare
- agent technology
- learning agents
- denial of service attacks
- bounded rationality
- decision making