Putting hidden text in web pages just to pwn AI agents for fun and profit sounds like a good time.

https://www.securityweek.com/google-deepmind-researchers-map-web-attacks-against-ai-agents/

#agenticai #posioning

Google DeepMind Researchers Map Web Attacks Against AI Agents

Threat actors can use malicious web content to set up AI Agent Traps and manipulate, deceive, and exploit visiting autonomous agents.

SecurityWeek
Scammers are poisoning AI search results to steer you straight into their traps - here's how - ZDNet Charlie Osborne #AI #LLMs #AIBrowsers #GoogleAIOverview #PerplexityComet #Posioning #searchresults
‘They told me we’re all Russians’: fears grow over ‘re-education’ of Ukrainian children

Russia, which boasts of taking in 700,000 children, stands accused of trying to erase their Ukrainian identity

The Guardian