Activate subscription >
Add devices or upgrade >
Renew subscription >
Secure Hub >
Don’t have an account? Sign up >
< Products
< Resources
< Help
A new type of attack can trick Microsoft Copilot for Word into spreading hidden prompt injections from document to document.
AI is making robocall scams cheaper, more convincing, and harder to spot. Here's why caller ID still isn't enough.
OpenAI has published an update on the incident in which one of its agents escaped its sandbox and accessed Hugging Face infrastructure.
An OpenAI agent escaped its sandbox, stole credentials, and broke into Hugging Face. Here's what that actually means.
A new selfie video verification feature could make recovering your Google Account easier. But it also creates new security and privacy concerns.
Samsung threatened to delete users' health data if they refused AI training. After a backlash, it quickly backed down.
The ClaudeBleed vulnerability still lets malicious Chrome extensions abuse Claude for Chrome's permissions.
A proof-of-concept attack hides prompt injection in a PNG file, turning routine code reviews into a path for secret theft.
Meta's new Muse Image tool lets anyone generate AI images of you from your public Insta profile. You won't be notified, and it's on by default.
