Skip to content

Ai Security

5articles

Articles

Security

Unauthorized Users Gained Access to Anthropic's Restricted Mythos AI Model

A group of forum members breached Anthropic's Mythos — an AI model designed to find vulnerabilities in operating systems and browsers. The company is investigating the incident.

April 23, 2026/3 min
Security

Ledger Unveils AI Security Roadmap to Protect Users in the Age of Autonomous Agents

Ledger has published its AI Security Roadmap 2026, outlining how the hardware wallet maker plans to secure digital assets as AI agents gain autonomous access to wallets and transactions.

April 14, 2026/3 min
Security

GPU Memory Attacks, $21B in Cybercrime Losses, and Chrome's Chip-Level Protection: Cybersecurity Roundup

The FBI reported record $21 billion in cybercrime losses for 2025, Google introduced hardware-bound session protection in Chrome, and researchers demonstrated three new attack methods targeting Nvidia GPU memory.

April 11, 2026/5 min
AI

Anthropic's Claude AI Discovered 22 Vulnerabilities in Firefox in Just Two Weeks

Anthropic tested Claude Opus 4.5's ability to find security flaws in Firefox. Out of 22 discovered vulnerabilities, 14 were classified as high-severity — accounting for a fifth of all critical bugs Mozilla fixed throughout 2025.

March 7, 2026/3 min
Security

PayPal Data Leak, OnlyFake Guilty Plea & AI Password Flaws

This week's key cybersecurity events: a PayPal bug exposed customer data, the OnlyFake fake documents platform creator pleaded guilty, and AI-generated passwords proved predictable.

February 28, 2026/6 min

Popular topics

Topics with the most content and project reviews