Start / The Data Exchange with Ben Lorica / Beyond guardrails defending llms against sophisticated attacks

The Data Exchange with Ben Lorica

Beyond Guardrails: Defending LLMs Against Sophisticated Attacks

45 min • 22 maj 2025

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.

Senaste avsnitt

From Human-Readable to Machine-Usable: The New API Stack

17 juli | 38 min

Why Voice Security Is Your Next Big Problem

10 juli | 42 min

Unlocking Unstructured Data with LLMs

3 juli | 28 min

Building Production-Grade RAG at Scale

26 juni | 31 min

Unlocking AI Superpowers in Your Terminal

19 juni | 45 min
Vad är en podd?

En liten tjänst av I'm With Friends. Finns även på engelska.

Podcastbild

00:00 -00:00
00:00 -00:00