Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse

Report 6242

Associated Incidents

Incident 12202 Report
LAMEHUG Malware Reportedly Integrates Large Language Model for Real-Time Command Generation in a Purported APT28-Linked Cyberattack

Loading...
UAC-0001 cyberattacks on the security and defense sector using the LAMEHUG software tool, which uses LLM (large language model) (CERT-UA#16039)
cert.gov.ua · 2025

AIID editor's note: See the original source of this report for the extra technical data that CERT-UA provides.

General information

On 10.07.2025, the National Cyber Incident, Cyber Attack, and Cyber Threat Response Team CERT-UA received information about the distribution among executive authorities, allegedly on behalf of a representative of the relevant ministry, of emails with an attachment in the form of the file "Appendix.pdf.zip".

The aforementioned ZIP archive contained an executable file of the same name with the extension ".pif", converted using PyInstaller from the source code developed in the Python programming language, classified by CERT-UA as a (malicious) software tool LAMEHUG.

During the investigation of the incident, at least two variants of the aforementioned software tool were additionally discovered in the form of the files "AI_generator_uncensored_Canvas_PRO_v0.9.exe", "image.py" with functional differences in the method of exfiltration of data from a computer.

It should be noted that a compromised email account was used to distribute emails, and the management infrastructure was deployed on legitimate, but compromised resources.

An obvious feature of LAMEHUG is the use of LLM (large language model), used to generate commands based on their text representation (description).

With a moderate level of confidence, the activity is associated with the activities of UAC-0001 (APT28).

LAMEHUG is a program developed using the Python programming language. Uses LLM Qwen 2.5-Coder-32B-Instruct via the API of the huggingface[.]co service to generate commands based on statically entered text (description) for their subsequent execution on a computer. In particular, it provides for the collection (and storage in the file "%PROGRAMDATA%\info\info.txt") of basic information about the computer (hardware, processes, services, network connections), as well as recursive search for Microsoft Office documents (including TXT, PDF) in the "Documents", "Downloads" and "Desktop" directories and their copying to the "%PROGRAMDATA%\info" folder. Exfiltration of the received information and files (in different versions of the program) can be carried out using SFTP or HTTP POST requests.

Read the Source

Research

  • Defining an “AI Incident”
  • Defining an “AI Incident Response”
  • Database Roadmap
  • Related Work
  • Download Complete Database

Project and Community

  • About
  • Contact and Follow
  • Apps and Summaries
  • Editor’s Guide

Incidents

  • All Incidents in List Form
  • Flagged Incidents
  • Submission Queue
  • Classifications View
  • Taxonomies

2024 - AI Incident Database

  • Terms of use
  • Privacy Policy
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • e1b50cd