AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.
Yifan ZengYiran WuXiao ZhangHuazheng WangQingyun WuPublished in: CoRR (2024)
Keyphrases
- multi agent
- ddos attacks
- defense mechanisms
- network security
- computer virus
- cooperative
- reinforcement learning
- countermeasures
- traffic analysis
- multiagent systems
- multi agent systems
- team formation
- malicious attacks
- agent oriented
- computer security
- intelligent agents
- intrusion detection
- dos attacks
- cooperative agents
- heterogeneous agents
- single agent
- multiple agents
- coalition formation
- cryptographic protocols
- security threats
- cyber attacks
- agent communication
- denial of service attacks
- security mechanisms
- multi agent planning
- advanced research projects agency
- information security
- anomaly detection
- chosen plaintext