Beyond Guardrails: Defending LLMs Against Sophisticated Attacks

The Data Exchange with Ben Lorica

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.