Beyond Guardrails: Defending LLMs Against Sophisticated Attacks

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.