Skip to main content

Tag: ai model hijack

1 article

Security analyst working at desk with gaming GPU and laptop displaying code.

Researchers Hijack Popular AI Model on Hugging Face Platform

Meet Alon Hertz, a security analyst who pulled off a mind-blowing experiment: he manipulated a popular AI model's output by simply tweaking its neural weights, leaving the rest of the system untouched. In just 87 seconds, he altered the model's voice output to produce poisoned audio, all without changing a single line of code.

Analyst 207