Forecasting the time of a cyber attack based on the results of non-stationary processes analysis

DOI: 10.31673/2409-7292.2020.034953

Abstract

The ability to predict cyberattacks before they occur will undoubtedly change the course of cyberwarfare and cybercrime. The problem with predicting cyberattacks is to obtain appropriate and reliable signals to counter cyber attackers. The article is based on machine learning methods and develops an integrated system for transforming large amounts of publicly available data to predict cyber incidents.

Keywords: Cybersecurity, forecasting, non-traditional signals.

References
1. D. Dagon, C. Zou, and W. Lee. Modeling botnet propagation using time zones. In Proceedings of the 13th Network and Distributed System Security Symposium (NDSS’06), 2006.
2. Neil Daswani, Michael Stoppelman, the Google Click Quality, and Inc Security Teams, Google. The anatomy of Clickbot.A. In USENIX First Workshop on Hot Topics in Understanding Botnets (HotBots), 2007
3. HoneynetProject, ―About the honeynet project,‖ 2008. http://www.honeynet.org/about
4. Project Honeypot [Електронний ресурс] – Режим доступу: https://www.projectHoneypot.org/
5. Amit D. Lakhani. Deception Techniques Using Honeypots. Dr. Kenneth G. Paterson Information Security Group Royal Holloway, University of London UK – 75 c.
6. HONEYPOT SECURITY: The Government of the Hong Kong Special Administrative Region. 2008 – 13 с
7. Caleb Townsend. What is a Honeypot? https://www.uscybersecurity.net/Honeypot
8. Securitycode. Что такое Honeypot и от чего защищать виртуальные ИС? 2011 https://habr.com/ru/company/securitycode/blog/119821