Skip to content
Sign inOpen the app
Decipher Security Podcast

More AI Model Escapes and New Backdoored Chinese Routers

Yesterday · 37 min · 35.7 MB
0:00-37:16

Streams straight from the publisher. podnod never proxies or re-hosts episode audio.

Open in podnod

We can't go a week without an AI model escaping its bounds, and this week we talk about a new test by the AI Security Institute in which OpenAI and Anthropic models escaped the evaluation environment and tried to start a supply chain attack, then we discuss news of Zbtlink routers having a persistent backdoor.