Source: Nbcnews
CrowdStrike disclosed that China-linked actors deployed DeepSeek's open-source LLM within the ARTEX tool to conduct reconnaissance and craft phishing attacks at scale. This is the first documented case of frontier AI models being operationalized in active intrusion campaigns—not as research or proof-of-concept, but with measurable tactical advantage against 200+ targets across 11 days. The speed and breadth suggest that open LLMs have crossed a threshold: they're no longer barriers to entry for sophisticated operators but force multipliers that compress reconnaissance-to-exploitation timelines. When the same models available to Fortune 500 security teams are equally available to state-sponsored actors, advantage shifts to whoever integrates fastest into existing attack infrastructure.