AI Security
Researchers hijack Hugging Face account for popular Kokoro AI model
Weak ownership checks let researchers take control of a widely used text-to-speech model
A Lack of ownership verification on the Hugging Face platform allowed researchers to take control of Kokoro, a text-to-speech model used in projects from Google, NVIDIA, AMD, Intel, and Amazon Web Services.
B
BleepingComputer
Source
BleepingComputer

AI Analysis
Generated insight by OnAirToday AI
The incident shows how weak ownership checks on a model-hosting platform can put widely used AI assets at risk. Because Kokoro is used in projects from major technology companies, account control can have implications beyond the model’s original account.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Security

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.