Smashing Security podcast #493: Why your AI model could be a sleeper agent

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.

This article has been indexed from GRAHAM CLULEY