bleepingcomputer.com/news/security/researchers-hijack-hugging-face-account-for-popular-kokoro-ai-model Researchers hijack Hugging Face account for popular Kokoro AI model
Researchers took over the Hugging Face account for Kokoro, a popular text-to-speech model, by registering a domain and resetting the publisher’s password. In a controlled test, they altered model weights so output diverged from input text without changing inference code, exposing supply-chain risks from unvetted updates.