AI Incident Database #1220 · 2025-07-10
LAMEHUG Malware Reportedly Integrates Large Language Model for Real-Time Command Generation in a Purported APT28-Linked Cyberattack
Ukraine's CERT-UA and Cato CTRL reported LAMEHUG, the first known malware to integrate a large language model (Qwen2.5-Coder-32B-Instruct via Hugging Face) for real-time command generation.
- Risk class (MIT)
- Cyberattacks, weapon development or use, and mass harm
- Reports
- 2
- Developers and deployers named
- 4
Reports
- Cato CTRL™ Threat Research: Analyzing LAMEHUG – First Known LLM-Powered Malware with Links to APT28 (Fancy Bear) · catonetworks.com, 2025-07-23
- Кібератаки UAC-0001 на сектор безпеки та оборони із застосуванням програмного засобу LAMEHUG, що використовує LLM (велику мовну модель) (CERT-UA#16039) · cert.gov.ua, 2025-07-17
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.