Browsing Tag
AI risk
2 posts
New “Cryptographic Context Injection” Leaks Grok Chat History in Zero-Click Exploit
Security researchers at Adversa AI have uncovered a new AI attack technique called Cryptographic Context Injection. The attack…
OpenAI Pauses Astra, Expands Daybreak GPT 5.6 Cyber
In a major shift for AI risk governance, OpenAI announced it has paused internal activities for its upcoming…