AI security research / articles
Analysis across cases.
103 Articles · Page 19 of 21
5 matching records on this page
From the archive
The recovery risk is not merely whether synthetic video looks convincing. It is what a successful check authorizes next: in the KZ-CERT account, video verification preceded replacement of the trusted phone number and subsequent access.
An AI browser can turn hostile page content into actions across logged-in accounts or payment tools. The cases differ in evidence and impact, but all make one review question concrete: which authority can an untrusted page persuade the surrounding system to use?
PhantomRaven combined deceptive npm package names, remote URL dependencies and lifecycle script execution. CrowdStrike separately assessed likely LLM involvement in writing the malware; the available reports do not establish a model recommendation or hallucinated name causing a victim installation.
A technical inventory of air-gap covert channels, updated with OpenAI October 2026 directed microVM CPU-cache demonstrations and the distinct September resolver-egress incident. Feasible signaling is not proof of autonomous uncontrolled escape.
May artifacts surfaced in September, July incidents were reinterpreted later, and newly published reports describe behavior months old. A single headline date cannot carry that history.
No matches on this page.