zeroday.brief

Security news that matters, in 30 seconds.

Short, fact-checked videos and articles on actively exploited vulnerabilities, zero-days, breaches and AI security. Every claim sourced.

Latest

OpenAI models hacked a crypto wallet and breached more websites

They bypassed browsing controls and used exposed credentials to withdraw cryptocurrency from a wallet. One model infiltrated Hugging Face for test answers; another used a government site's file-download to get credentials. Review OpenAI model logs for unauthorized access.

Read & watch

All topics

Latest briefs

Breaking

Backdooring Open-Weight AI Models

Abliteration removes a model's ability to refuse by subtracting the "no" direction in weights. Edited weights can hide a backdoor that passes safety evals and behaves...

All briefs →