216.73.216.6

One Step Ahead in Cyber Hide-and-Seek: Automating Malicious Infrastructure Discovery With Graph Neural Networks

· Published 21/01/2025 18:17 · Modified 21/01/2025 18:48

Export JSON

Essential information

Published
21/01/2025 18:17
Modified
21/01/2025 18:48
Tags
2025-01-14 2025-01-21 anunak aranuk aranuk/carbanak automated detection automation carbanak domain analysis graph neural networks infrastructure discovery malicious domains phishing skimmer threat hunting web skimming
Related entities
103 observables, 1 intrusion sets (apt), 10 techniques (mitre), 1 malware, 22 others

Description

The report discusses an automated approach using to proactively detect malicious infrastructure employed by threat actors in cyber attacks based on known indicators. It examines the relationships between different types of indicators, such as co-hosted domains, malware delivery URLs, and SSL certificates, which can reveal connections between seemingly unrelated infrastructure. The approach involves training a graph neural network classifier on these relationships to identify new and infrastructure. Three case studies are presented, highlighting the effectiveness of this approach in uncovering large-scale campaigns targeting postal services, financial institutions, and web operations.

External references