Researchers seize Hugging Face account for Kokoro text-to-speech model
Security researchers led by Alon Hertz took control of the Hugging Face account for Kokoro, a popular open-weight text-to-speech model, by registering the expired domain listed as the developer's contact and using it to reset the account's password. They then demonstrated that an attacker could quietly alter the model's neural weights so it generates audio diverging from input text, without modifying any application code. Kokoro, abandoned by developer Hexgrad since April 2025, still receives nearly 13 million monthly downloads and is used in tools from Google, NVIDIA, AMD, Intel and AWS.
GoKawiil's interpretation of the reporting above, not reported fact.
Because the attack changes only model weights rather than code, it leaves no signature for conventional malware scanners to catch, which could let tampered models slip through supply-chain defenses undetected. The incident highlights a broader weakness in how AI model repositories verify ownership, especially for abandoned but widely-used projects integrated into major vendors' developer tools. It suggests companies relying on open-weight models may need new methods to verify model integrity beyond code review.
- Researchers hijacked Kokoro's Hugging Face account by registering its expired domain and resetting the password.
- They showed model weights alone can be altered to change output without touching any application code, evading malware scanners.
- Kokoro, unmaintained since April 2025, is still used by Google, NVIDIA, AMD, Intel and AWS tools, with ~13M monthly downloads.
Source: bleepingcomputer.com, 2026-11-17
Published there as: “Researchers hijack Hugging Face account for popular Kokoro AI model”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.