AI & ML
Smashing Security podcast #493: Why your AI model could be a sleeper agent
Graham Cluley0 views
You join a video call, and your contact and a few colleagues are already there, waiting patiently. But they can't hear you, and a pop-up says you need to install an update to fix your microphone. What could possibly go wrong? Meanwhile, we explain how changing just a handful of numbers can turn an AI model into a sleeper agent, waiting for the right moment to strike. Plus, Andrius Buinovskis of NordLayer explains how companies can see which AI tools their staff are really using, and stop sensitive data leaking out, without banning AI altogether. All this and more in episode 493 of the "Smashing Security" podcast with cybersecurity expert and keynote speaker Graham Cluley, and special guest Ray Redacted.
Source:https://grahamcluley.com/smashing-security-podcast-493/PreviousInstagram Now Lets You Save Songs to Apple MusicNextProton’s Lumo AI chatbot is now available on Linux desktops
Related posts

Running Claude Code, Codex and Cursor at the same time? 8 Mac apps that keep three agents from becoming chaos (2026)
0dev.to AI
Google launches Gemini 4 Neon, its Gemini 4 model for coding and knowledge work, at $3/$15 per million tokens
0dev.to AI
Image models can paint a torii. They still invent the 営業時間
0dev.to AI

Gemma 4 on AWS Lambda with a GPU: E2B on an NVIDIA L4, Day One
0dev.to AWS

Keep an AI Coding Handoff Reproducible After One File Changes
0dev.to WebDev

Worse Than AI Cheating: 20 Widely Used AI Models Were Tricked Into Dangerous Actions, and All 20 Went Along
0dev.to Security