使用Player FM应用程序离线!
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678
Manage episode 410063625 series 2355587
Today we're joined by Jonas Geiping, a research group leader at the ELLIS Institute, to explore his paper: "Coercing LLMs to Do and Reveal (Almost) Anything". Jonas explains how neural networks can be exploited, highlighting the risk of deploying LLM agents that interact with the real world. We discuss the role of open models in enabling security research, the challenges of optimizing over certain constraints, and the ongoing difficulties in achieving robustness in neural networks. Finally, we delve into the future of AI security, and the need for a better approach to mitigate the risks posed by optimized adversarial attacks.
The complete show notes for this episode can be found at twimlai.com/go/678.
710集单集
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Manage episode 410063625 series 2355587
Today we're joined by Jonas Geiping, a research group leader at the ELLIS Institute, to explore his paper: "Coercing LLMs to Do and Reveal (Almost) Anything". Jonas explains how neural networks can be exploited, highlighting the risk of deploying LLM agents that interact with the real world. We discuss the role of open models in enabling security research, the challenges of optimizing over certain constraints, and the ongoing difficulties in achieving robustness in neural networks. Finally, we delve into the future of AI security, and the need for a better approach to mitigate the risks posed by optimized adversarial attacks.
The complete show notes for this episode can be found at twimlai.com/go/678.
710集单集
すべてのエピソード
×欢迎使用Player FM
Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。