72 min listen
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678
FromThe TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678
FromThe TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
ratings:
Length:
48 minutes
Released:
Apr 1, 2024
Format:
Podcast episode
Description
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.
The complete show notes for this episode can be found at twimlai.com/go/678.
Released:
Apr 1, 2024
Format:
Podcast episode
Titles in the series (100)
Scaling Deep Learning: Systems Challenges & More with Shubho Sengupta — TWiML Talk #14: This week my guest is Shubho Sengupta, Research S… by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)