How Hackers Attack AI Agents in 2026 — The Complete Threat Model

A single sentence from M-Trends 2026 — released this week — captures the 2026 AI threat landscape: adversaries are integrating AI to accelerate the attack lifecycle. My deeper version: adversaries aren't just using AI to write better phishing emails — they're targeting AI systems directly, exploiting the AI as the attack vector, and deploying AI as autonomous attack agents. Here's the complete 2026 threat model for AI agent security, built from the documented incidents and the attack patterns Mandiant, IBM…

Read full article →

How to Use AI for Cybersecurity Without Creating New Risks in 2026

AI is the most significant capability change in defensive security since endpoint detection and response emerged as a category. My experience over the past two years is that the organisations getting the most value from AI security tools share a common characteristic: they defined measurable success criteria before deployment, not after. The organisations I work with that are getting the most value from AI security tools share a common pattern: they deployed AI to augment existing capabilities rather than replace…

Read full article →