OpenAI Expands ChatGPT Lockdown Mode to Millions of Eligible Users
ChatGPT’s stricter security mode is getting a wider release. OpenAI is making Lockdown Mode, an optional setting in ChatGPT that...
Data exfiltration
FBI Warns Companies About Ransom Gang’s Fake IT Support Tactics
For some ransomware crews, the fastest route to a payout may no longer be locking systems. It may be walking...
Indirect Prompt Injection Is Now a Real-World AI Security Threat
Last week, researchers at Google and Forcepoint reported that indirect prompt injection — a category of attack the security community...
GrafanaGhost: The AI That Leaked Everything Without Being Hacked
Image: Prostock-studio/Adobe No credentials were stolen. No alerts were triggered. And yet, the data slipped out anyway. On April 7,...
AI Agents Are Quietly Redefining Enterprise Security Risk
Image: GoldenDayz/Envato A new social network called Moltbook launched in late January with a premise that should unsettle every CISO...
