Critical Thinking - Bug Bounty Podcast cover image

Episode 101: CTBB Hijacked: Rez0__ on AI Attack Vectors with Johann Rehberger

Critical Thinking - Bug Bounty Podcast

00:00

Techniques for Extracting Information from Language Models

This chapter explores various techniques for extracting information from systems using large language models. It covers methods to bypass restrictions, including language manipulation and data exfiltration strategies.

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