← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Researchers Hijack Hugging Face Account for Popular Kokoro AI Model via Domain Re-registration

🔄 Updated 4d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Researchers hijacked the Hugging Face account for the Kokoro AI model.
  • They used domain re-registration to reset the account password.
  • Modified model weights to alter audio output without code changes.
  • Kokoro is used by Google, NVIDIA, AMD, Intel, and AWS projects.

Account Hijack Method

Security researchers successfully gained control of the Hugging Face account associated with Kokoro, an open-weight text-to-speech model. The method involved registering the 'hexgrad.com' domain, which was listed in Kokoro's public DONATE.md file and used by the original developer, Hexgrad. After registering the domain, the researchers used it to perform a password reset on the publisher's Hugging Face account.

Demonstrated Attack Vector

With control of the account, the researchers demonstrated a supply-chain attack by modifying the Kokoro model's weights. This modification caused the model to produce audio that differed from the input text, even though the underlying application code remained unchanged. This type of attack is difficult to detect with traditional malware scanners because no malicious code or signature is introduced into the application itself, only the model's internal parameters are altered.

Impact and Usage of Kokoro

Kokoro is a popular text-to-speech model supporting multiple languages and over 50 voice presets, with nearly 13 million monthly downloads on Hugging Face. Despite its developer not pushing updates since April 2025, the model is integrated into developer tools and workflows from major tech companies, including Google, NVIDIA, AMD, Intel, and Amazon Web Services. This widespread use highlights the potential impact of such a supply-chain compromise.

Stealthy Model Poisoning

The researchers emphasized the stealthy nature of the attack. As researcher Alon Hertz stated, they changed what the model says by fine-tuning its neural weights, keeping the input text, voice file, configuration, and inference code identical. The team tested the modified model locally but did not upload the poisoned weights to Hugging Face to avoid compromising production systems. They also noted that Hugging Face did not flag such modifications as suspicious in their tests.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

Security researchers took control of the Hugging Face account for Kokoro, a widely used text-to-speech AI model, by re-registering the developer's expired domain and resetting the password. This vulnerability allowed them to demonstrate how an attacker could modify the model's weights to produce altered audio output without changing application code, posing a supply-chain risk for projects using the model.