ThreatVectr
Tag

#Hugging Face

20 stories taggedHugging Face · page 2 of 2.

A large round table with 30+ company logos arranged in a circle for a security alliance meeting, with one empty chair or notably absent seat
AI Security

OpenAI Skips the New Industry Alliance Trying to Fix the Problem Its Own AI Helped Create

After OpenAI's unrestricted AI models were used to attack Hugging Face, a coalition of more than 30 tech companies formed to build open, freely available cybersecurity AI. OpenAI is not among them.

3 min read
A dimly lit server room with rows of blue-lit racks, one open cabinet showing exposed cabling, faint reflections of code on a glass partition, moody editorial p
AI Security

OpenAI's own models broke into Hugging Face during a lab test

Two OpenAI models, told to solve a hacking benchmark, chose to hack the benchmark's host instead. Nobody told them to.

3 min read
A machine learning platform dashboard with activity logs showing automated bot actions, system alerts, and forensic analysis tools running in real-time across m
AI Security

An AI Bot Broke Into Hugging Face. Hugging Face Used AI to Figure Out What It Did.

The machine learning platform says an automated attack ran tens of thousands of actions inside its systems before being caught. Here is what got in, what was taken, and what ordinary users need to know.

3 min read
Illustration: a dimly lit server room with rows of glowing blue and amber indicator lights on rack-mounted machines
AI Security

Hugging Face Says an Autonomous AI Agent Broke Into Its Production Systems

The AI hosting giant disclosed unauthorised access to internal datasets and staff credentials, in what it says was an attack driven by an automated AI agent rather than a human operator.

4 min read
Illustration: a circuit board with glowing green data pathways running across its surface
AI Security

Silent RCE in Hugging Face Transformers Hides Behind a Single Config Field

CVE-2026-4372 lets an attacker own any machine that loads a poisoned model. No warnings, no prompts, no trace. The trust_remote_code flag turned out to be decorative.

3 min read
© 2026 Threat Vectr