#agent-vulnerabilities

[ follow ]
#ai-security #prompt-injection #deepmind #content-injection #adversarial-training #data-exfiltration #ai-agents
Information security
fromnews.bitcoin.com
1 week ago

Deepmind's 'AI Agent Traps' Paper Maps How Hackers Could Weaponize AI Agents Against Users

Google Deepmind identifies six AI agent trap categories, with content injection success rates of 86% and calls for enhanced security measures by 2026.
fromInfoWorld
3 months ago

Building AI agents the safe way

As Willison has been cataloguing for years on his blog, we keep making the same key mistake building with AI as we did in the web 2.0 era: We treat data and instructions as if they are the same thing. That mistake used to give us SQL injection. Now it gives us prompt injection, data exfiltration, and agents that happily (confidently!) do the wrong thing at scale.
Information security
Artificial intelligence
fromZDNET
5 months ago

Microsoft researchers tried to manipulate AI agents - and only one resisted all attempts

Industry-leading agentic AI tools struggle with basic marketplace interactions and are frequently vulnerable to manipulation, producing unreliable autonomous decisions.
[ Load more ]