The Azure Security Podcast cover image

Episode 90: AI Red Teaming

The Azure Security Podcast

00:00

The Interplay Between Language and AI Models

In this chapter, the speakers discuss the interplay between language and artificial intelligence (AI) models. They mention a recent research paper that examines the use of persuasive language in jailbreak attempts and how it compares to security controls. They highlight that the understanding of language in AI models is still evolving and falls somewhere between social engineering and technical manipulation.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app