Optimal Machine Learning Algorithms for Cyber Threat Detection

Оптимальные алгоритмы машинного обучения для обнаружения киберугроз
Hafiz M. Farooq, Naif M. Otaibi, Hafiz Umar Farooq
2018-03-01

Security Operations Center (SOC)cyber threat detectionfalse-positive detectionmachine learning algorithmssecurity log analytics
With the exponential hike in cyber threats, organizations are now striving for better data mining techniques in order to analyze security logs received from their IT infrastructures to ensure effective and automated cyber threat detection. Machine Learning (ML) based analytics for security machine data is the next emerging trend in cyber security, aimed at mining security data to uncover advanced targeted cyber threats actors and minimizing the operational overheads of maintaining static correlation rules. However, selection of optimal machine learning algorithm for security log analytics still remains an impeding factor against the success of data science in cyber security due to the risk of large number of false-positive detections, especially in the case of large-scale or global Security Operations Center (SOC) environments. This fact brings a dire need for an efficient machine learning based cyber threat detection model, capable of minimizing the false detection rates. In this paper, we are proposing optimal machine learning algorithms with their implementation framework based on analytical and empirical evaluations of gathered results, while using various prediction, classification and forecasting algorithms.
1
Machine-learning analytics are presented as a means to mine security logs, detect advanced targeted threats, and reduce reliance on static correlation rules.
2
Selecting an appropriate machine-learning algorithm remains a major challenge because false-positive detections can undermine cybersecurity data-science deployments.
3
The paper proposes an implementation framework for selecting optimal machine-learning algorithms using analytical and empirical evaluation of prediction, classification, and forecasting methods.
4
The proposed approach targets reduced false-detection rates, particularly for large-scale or global Security Operations Center environments.

security logs from IT infrastructures

machine-learning-based cyber threat detection, focusing on algorithm selection and minimizing false-positive detection rates

Publication Details
Publication Date
2018-03-01
Journal
Publisher
ISSN
Cited by
58
Access Type
Author Information
Authors
Hafiz M. Farooq
Naif M. Otaibi
Hafiz Umar Farooq
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%