Major AI developers’ model-safety claims rest on incorrect assumptions about how hackers behave, Cisco researchers said in a ...

One malicious prompt gets blocked, while ten prompts get through. That gap defines the difference between passing benchmarks and withstanding real-world attacks — and it's a gap most enterprises don't ...

Cisco researchers show how leading AI models wither under realistic multi-turn attacks, calling into question the value of ...

A new report out today from Cisco Systems Inc. argues that none of the closed flagship large language models it tested can be ...

University researchers were able to embed hidden signals in audio clips that silently commandeer AI model behavior.

Researchers say the technique can manipulate how vision-language models interpret both images and user prompts.

A tech industry executive from Palo Alto Networks offers a preview of how emerging AI models will soon disrupt the security ...