Episode Details
Back to EpisodesBeyond 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.