Skip to content
Researchers Compromise Hugging Face Account for Kokoro AI Model

Researchers Compromise Hugging Face Account for Kokoro AI Model

First seen 18 Nov 2026, 11:18 UTC • •

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •November 18, 2026 at 11:19 UTC
  • •Researchers hijacked the Kokoro AI model account on Hugging Face.
  • •The attack involved modifying model weights to produce altered outputs without detection.
  • •Hugging Face does not verify publisher ownership, increasing supply-chain risks.

Security researchers gained control of the Kokoro text-to-speech model on Hugging Face, exposing vulnerabilities in AI model management. By registering an expired domain linked to the model's publisher, they reset the account password and modified the model's neural weights to produce altered audio outputs without changing the application code. This attack method allows for undetectable malicious changes, as traditional malware scanners cannot identify the compromise. Kokoro is widely used in projects by major companies like Google, NVIDIA, AMD, Intel, and Amazon Web Services. The researchers emphasized that Hugging Face lacks publisher ownership verification, enabling potential supply-chain attacks. The incident highlights significant trust issues in the open-model ecosystem, as even legitimate accounts could be exploited to distribute harmful content.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Timeline

2026-11-17
Researchers gain control of Kokoro account
Security researchers registered the expired domain of Kokoro's publisher to reset the account password and modify the model's weights.
Bleepingcomputer
2026-11-18
Supply chain risks highlighted
The researchers reported that Hugging Face's lack of publisher verification allows for potential distribution of manipulated AI components.
Feeds.Feedburner

More articles in this cluster (6)

Following this threat?

Track Amazon Web Services in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Common questions

How did the researchers gain access?
They registered an expired domain associated with Kokoro's publisher and reset the account password.
What are the implications of this attack?
The attack allows for undetectable alterations to AI model outputs, posing significant supply-chain risks.
Is there a fix for this vulnerability?
Currently, there is no fix as Hugging Face does not verify publisher ownership, which remains a critical oversight.