Artificial Intelligence Google DeepMind Researchers Map Web Attacks Against AI Agents A vulnerability named ‘AI Agent Traps’ allows attackers to manipulate, deceive, and exploit visiting agents via malicious web content. Ionut ArghireApril 6, 2026
Artificial Intelligence Google DeepMind’s New AI Agent Finds and Fixes Vulnerabilities The new product is called CodeMender and it can rewrite vulnerable code to prevent future exploits. Eduard KovacsOctober 8, 2025
Artificial Intelligence Google DeepMind Unveils Defense Against Indirect Prompt Injection Attacks Google DeepMind has developed an ongoing process to counter the continuously evolving threatIndirect prompt injection (IPI) attacks. Kevin TownsendMay 21, 2025
Artificial Intelligence Google DeepMind Unveils Framework to Exploit AI’s Cyber Weaknesses DeepMind found that current AI frameworks are ad hoc, not systematic, and fail to provide defenders with useful insights. Kevin TownsendApril 2, 2025