Agentic AI Frontier Online Seminar: AI Security Talk
Notice: Heads up: This article was published more than 6 months ago. Details, links, or policies may have changed since then.
Join Prof. Furong Huang’s talk on AI security at the Agentic AI Frontier Online Seminar on Sept 5, 2025, discussing stress-testing and alignment in LLMs.
Join the AI Agent Frontier Online Seminar on September 5th, 2025, as Prof. Furong Huang discusses ‘Towards AI Security – An Interplay of Stress-Testing and Alignment’.
Key discussion points include:
- Stress-testing approaches to expose vulnerabilities in large language models (LLMs)
- Challenges such as hallucinations, jailbreaking, and poisoning attacks
- Alignment methods to embed ethical and security constraints into model behavior
To join via Zoom, click here. Passcode: 309194
For more information on the seminar, visit the AI Agent Frontier Online Seminar Homepage.
Tags: AI Security, Agentic AI, LLMs, Stress-Testing, AI Alignment, AI Seminar