Episode Details

Back to Episodes

Beyond Guardrails: Defending LLMs Against Sophisticated Attacks

Published 10 months, 4 weeks ago
Description

Jason Martin is an AI Security Researcher at HiddenLayer. This episode explores “policy puppetry,” a universal attack technique bypassing safety features in all major language models using structured formats like XML or JSON.

Subscribe to the Gradient Flow Newsletter 📩  https://gradientflow.substack.com/

Subscribe: Apple · Spotify · Overcast · Pocket Casts · AntennaPod · Podcast Addict · Amazon ·  RSS.

Detailed show notes - with links to many references - can be found on The Data Exchange web site.

Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us