AI Security Interview Series: LLM Security and Abuse Cases
HTML-код
- Опубликовано: 26 авг 2024
- In this installment of our AI security interview series, we bring you to a conversation with Daniel Kang, Professor at UIUC, moderated by Hyrum Anderson, CTO of Robust Intelligence. Leveraging his numerous works on AI security, Daniel enlightens us on the capabilities and abuse cases of LLMs and AI agents. During this session, he discusses vulnerability discoveries, the risks and attacks associated with AI agents, and the safe harbor for AI evaluation red teaming.
Love to have the link of paper here..