Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.
Zhichen DongZhanhui ZhouChao YangJing ShaoYu QiaoPublished in: CoRR (2024)
Keyphrases
- denial of service attacks
- dos attacks
- denial of service
- network security
- countermeasures
- malicious attacks
- ddos attacks
- security vulnerabilities
- natural language
- security threats
- human agent
- safety analysis
- conversational agent
- traffic analysis
- spam filters
- multi party
- attack detection
- turn taking
- cooperative
- machine learning
- malicious users
- neural network