Detecting sleeper agents hiding in AI model neurons

Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than ten neurons to inject a short payload; Microsoft Research has also found that this threat is detectable by frontier agents, which can identify anomalous weight edits. The post Detecting sleeper agents hiding in AI model neurons appeared first on Microsoft Security Blog.

This page shows only the headline and the short summary. The full text is published by the original source.