SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact UsThis paper presents an evaluation of a locally deployable open-weight large language model tested across five prompt strategies of increasing sophistication against a corpus of real-world cyber incident reports, scored against a structured rubric by both an AI instrument and an independent human analyst.




















