Attackers can use indirect prompt injections to trick Anthropic’s Claude into exfiltrating data the AI model’s users have ...

New SPLX research exposes “AI-targeted cloaking,” a simple hack that poisons ChatGPT’s reality and fuels misinformation.

The Transportation Security Administration (TSA) has a program called 'KCM (Known Crewmember)' that allows pilots and flight attendants to pass security checks even when they are off. Similarly, there ...

ChatGPT Atlas is a new agentic browser that can browse the internet almost on your behalf, but this is more dangerous than ...

A new attack called 'CometJacking' exploits URL parameters to pass to Perplexity's Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and ...