B-SWARM prototype

Quick Overview

B-Swarm is a distributed data mining-based approach for intelligence collection and incident response awareness (source code released under a GPLv3 license). This approach uses multiple positions on the Internet (i.e., vantage points and collector instances) to interact with the specified online resources (e.g., URLs). The representation of the same information source is collected and evaluated from multiple perspectives to identify significant content changes among them.

Publications

This work has been described in further detail in the following resources:

1. B.Blumbergs (2024). Black Sheep Wall: Towards Multiple Vantage Point-based Information Space Situational Awareness. In proceedings of 21st International Conference on Security and Cryptography (SECRYPT 2024). SCITEPRESS. Dijon, France
2. B.Blumbergs (2024). Black Sheep Wall: Clearing the Fog-of-War for Cyber Intelligence Collection. ArcticSecurity Public Exposure blog
3. B.Blumbergs (2023). A Multiple Vantage Point-based Concept for Open-Source Information Space Awareness (technical report). In Information and Communication System Security (ICSS) technical workshop. Sapporo, Japan.

Validation Datasets

Validation data sets are available on the following resources (released under MIT license):

1. Files.fm
2. Mega.nz

Acknowledgements

The project has been supported by the Japanese Society for the Promotion of Science (JSPS) post-doctoral fellowship (2023-2024). The research has been facilitated by the Nara Institute of Science and Technology (NAIST) Laboratory of Cyber Resilience (prof. Kadobayashi laboratory).