AI security research / articles
Analysis across cases.
43 Articles · Page 9 of 9
3 matching records on this page
From the archive
Anthropic's September threat report describes three campaigns where agents handled parallel reconnaissance, exploitation, malware adaptation and data collection. The underlying exploits are familiar; the operating model is changing.
OpenAI, Anthropic, AISI and Google/Irregular exposed different paths from an evaluation objective to real systems. Together they make one old assumption difficult to keep: the sandbox is only one part of the boundary.
A wiki edit, a malicious pull request and a package upload are different actions, but all turn the public internet into persistent state outside the intended task.
No matches on this page.