Conventional Cybersecurity Won’t Protect Your AI

In June 2025, researchers uncovered a vulnerability that exposed sensitive Microsoft 365 Copilot data without any user interaction. Unlike conventional breaches that hinge on phishing or user error, this exploit, now known as EchoLeak, bypassed human behavior entirely, silently extracting confidential information by manipulating how Copilot interacts with user data. The incident highlights a sobering…

Read More

Do Monkeys Make Faces on Purpose?

January 8, 2026 2 min read Add Us On GoogleAdd SciAm Do Monkeys Make Faces on Purpose? A new study suggests that primate facial expressions may not just be reflex By Cody Cottier edited by Sarah Lewin Frasier Macaques’ threatening grins and friendly lip-smacks may be partially intentional. Christophe Lehenaff/Getty Images Facial expressions are central…

Read More

The 11 runtime attacks breaking AI security — and how CISOs are stopping them

Enterprise security teams are losing ground to AI-enabled attacks — not because defenses are weak, but because the threat model has shifted. As AI agents move into production, attackers are exploiting runtime weaknesses where breakout times are measured in seconds, patch windows in hours, and traditional security has little visibility or control. CrowdStrike’s 2025 Global…

Read More
Back To Top