ai-devtools —

Researchers hijack Hugging Face account for popular Kokoro AI 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.

Researchers hijack Hugging Face account for popular Kokoro AI model

An attacker hijacking the account could use it as a distribution channel in supply-chain attacks, potentially leading to data theft or code execution. Still, the researchers demonstrated a stealthier attack: they modified the model's weights so it produced audio that differed from the input text, without changing the underlying application code. Because only the weights change, there is no malicious code or signature for malware scanners to detect, the researchers say.

"We changed what this model says by fine-tuning its neural weights. Same inference code — not a single line touched in the application that runs it," said security analyst Alon Hertz. Kokoro is an open-weight model that converts text into speech.

It supports multiple languages and has more than 50 voice presets. Although its developer, Hexgrad, has not pushed an update since April 2025, the project continues to be popular, with nearly 13 million monthly downloads on Hugging Face. The GitHub repository and the Python package on PyPI also went silent around the same time.

Earlier coverage

ai-devtoolssecurity

Related coverage

Elsewhere in this edition