OpenAI AI models went rogue during testing, triggering 'unprecedented' breach at startup

By Raphael Satter WASHINGTON, July 21 (Reuters) - OpenAI said on Tuesday that an autonomous agent powered by its advanced ...

Google launches a cheaper alternative to large AI security models like Mythos

Anthropic’s Mythos 5 is a powerful AI security model released as part of the company’s Project Glasswing initiative. The ...
FingerLakes1.com

OpenAI and Hugging Face Partner After Model Security Incident During Testing

OpenAI and Hugging Face announce new partnership after model security incident during testing. The aim of the collaboration ...
American Banker

OpenAI models' Hugging Face breach is a red flag for bankers

The intrusion did not affect the financial industry directly. But it presents a warning to banks that are deploying agentic ...
SiliconANGLE

Cisco unveils new AI-driven security innovations at RSAC 2025 to address growing threat complexity

Cisco Systems Inc. today introduced a slate of new security innovations at the annual RSAC Conference 2025 in San Francisco that are focused on helping enterprises navigate artificial intelligence ...
VentureBeat

How open-source LLMs enable security teams to stay ahead of evolving threats

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Open-source large language models (LLMs) ...
VentureBeat

Five signs data drift is already undermining your security models

Data drift happens when the statistical properties of a machine learning (ML) model's input data change over time, eventually rendering its predictions less accurate. Cybersecurity professionals who ...
Dark Reading

To Spot Attacks Through AI Models, Companies Need Visibility

As companies rush to develop and test artificial intelligence and machine learning (AI/ML) models in their products and daily operations, the security of the models is often an afterthought, putting ...
War on the Rocks

High-Risk AI Models Need Military-Grade Security

The race to develop artificial general intelligence is accelerating, but America’s approach to securing it remains dangerously inadequate. While Washington celebrates its new “AI Action Plan,” which ...
Forbes

Zero‑Trust AI: The New Security Model For Enterprise LLMs

Enterprises are racing to embed large language models (LLMs) into critical workflows ranging from contract review to customer support. But most organizations remain wedded to perimeter-based security ...
CSOonline

AI is breaking traditional security models — Here’s where they fail first

Traditionally, enterprise security operating models operated a fixed and regular cycle: Findings surfaced through periodic scans, security teams triaged results and remediation followed through ticket ...

OpenAI says AI models went rogue during testing, triggering ‘unprecedented’ breach at startup

The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that ...