Home ยป Report: Vulnerability on Hugging Face Allows for Sending Models to Penetrate Other Users’ AI.

Report: Vulnerability on Hugging Face Allows for Sending Models to Penetrate Other Users’ AI.

Wiz, a cloud security company, has reported a serious vulnerability found on the Hugging Face AI model platform, allowing access to other users’ AI model data.

The security engineering team at Wiz utilized a method of reverse engineering by uploading their own malicious model onto Hugging Face and then exploiting the system at the container level, granting access to other users’ model data on the platform.

The two critical vulnerabilities discovered by Wiz that enabled this exploit were the AI Inference component commonly using the pickle format, allowing for the execution of unsafe commands, and the ability for CI/CD processes to run consecutively, making it possible to exploit the system and manipulate CI/CD clusters.

These vulnerabilities have been reported and addressed by Hugging Face, with Wiz announcing a collaboration to enhance security measures on the platform moving forward.

TLDR: Wiz identified and exploited vulnerabilities on the Hugging Face platform, leading to a collaboration to enhance security measures.

More Reading

Post navigation

Leave a Comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Windows 11 Faces Screen Capture Feature Recall by Microsoft, Emphasizing Proper Shutdown to Prevent Data Encryption Complications

Government of Japan Prepares to Order LINE to Separate its System from NAVER After Data Breach in Late 2023.

Collaboration of Intel and AMD in Architecting x86 Technology to Challenge Arm as a Unified Force