Hosted on MSN

Popular Python libraries used in Hugging Face models subject to poisoned metadata attack

Vulnerabilities in popular AI and ML Python libraries used in Hugging Face models with tens of millions of downloads allow remote attackers to hide malicious code in metadata. The code then executes ...
TechRepublic

Malicious Hugging Face Models Could Trigger Remote Code Execution

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks. Image: Robert – stock.adobe.com Organizations using ...
SiliconANGLE

Critical Hugging Face Transformers flaw ran attacker code on a routine model load

Pluto Security Inc. today disclosed a critical remote code execution vulnerability in Hugging Face Inc.’s Transformers library that allowed attacker-controlled artificial intelligence models to run ...

Transformers Adds Native GGUF Support — The Light and Shadow of Apple LensVLM and MiMo-V2.6 Benchmarks

This article has been edited and created by AI.Transformers Adds Native GGUF Support — The Light and Shadow of Apple LensVLM and MiMo-V2.6 BenchmarksHugging Face has integrated native support for GGUF ...