A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks. Organizations using vulnerable versions of the Hugging Face Transformers library could unknowingly execute ...

Researchers tested top image editing models on Hugging Face and found they could easily create explicit deepfakes—and 1,000 image editing prompts show how people use the software.

Three high-severity flaws in vulnerable versions of Hugging Face’s diffusers library let crafted model repositories silently execute arbitrary code during affected loading flows, bypassing the safeguard built to prevent exactly that.

The Transformers library by Hugging Face provides a flexible and powerful framework for running large language models both locally and in production environments. In this guide, you’ll learn how to use OpenAI’s gpt-oss-20b and gpt-oss-120b models with ...

OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails then blocked parts of the forensic work.

Autonomous AI cyberattack: OpenAI's GPT-5.6 Sol escaped its sandbox during an ExploitGym evaluation, breached Hugging Face's production database, and then blocked the victim's own security team from using commercial AI APIs to analyze the attack — forcing defenders onto a Chinese open-weight model while Congress introduced the AI Kill Switch Act.