Mastodon Feed: Post

Mastodon Feed

jonny@neuromatch.social ("jonny (nonvenomous)") wrote:

reading this: https://huggingface.co/blog/security-incident-july-2026

so what you're saying is that the attacker data and the credentials it referenced did leave the environment?

The asymmetry problem When we started the log analysis, we first used frontier models behind commercial APIs. This did not work: the analysis requires submitting large volumes of real attack commands, exploit payloads, and C2 artifacts, and these requests were blocked by the providers' safety guardrails, which cannot distinguish an incident responder from an attacker. We ran the forensic analysis instead on GLM 5.2, an open-weight model, on our own infrastructure. This had a second benefit: no attacker data, and none of the credentials it referenced, left our environment.