
AI cyberattacks: Defending against offensive agents
Nov 1, 20262 min read
As AI cyberattacks shift from theory to active agentic intrusions, securing your models is critical. Learn how to lock down AI workflows against autonomous threats.
Read MoreCategory
Breaches, vulnerabilities and how to stay safe.

Nov 1, 20262 min read
As AI cyberattacks shift from theory to active agentic intrusions, securing your models is critical. Learn how to lock down AI workflows against autonomous threats.
Read More
Oct 30, 20262 min read
Epoch AI researchers proved an open-weight model can autonomously build Firefox exploits in under 48 hours for just $1,000, turning public security fixes into instant threats.
Read More
Oct 28, 20263 min read
Unreleased AI models are now building complex exploit chains across major operating systems. We look at the concrete threat and how developers must respond.
Read More
Oct 27, 20262 min read
October 2026 brought a massive wave of software vulnerabilities and supply chain attacks. We look at the critical PHP updates and how AI is changing both attack and defense.
Read MoreThese posts follow breaches, vulnerabilities and supply chain attacks from the point of view of people who run software, such as the PHP flaws and AI-assisted exploit chains of Black October. The tools below cover small, practical checks.