Clustering method for security events based on attention mechanism

Guoliang Lu; Xue Jia; Shuqi Wang; Hao Yu

doi:10.1117/12.3034874

7 August 2024 Clustering method for security events based on attention mechanism

Guoliang Lu, Xue Jia, Shuqi Wang, Hao Yu

Author Affiliations +

Proceedings Volume 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024); 1322415 (2024) https://doi.org/10.1117/12.3034874
Event: 4th International Conference on Internet of Things and Smart City, 2024, Hangzhou, China

Abstract

Network security analysts in the daily monitoring and research work, will deal with a large number of security events, through the behavioral analysis of the details of the security event analysis and context correlation analysis to determine whether the real attack, and then according to the results of the research and judgment to be disposed of. These security events often originate from different brands of security equipment, and in the face of massive security event logs, it is difficult for analysts to consider all aspects, and omissions and misjudgments will inevitably occur. In this paper, we provide a security event clustering method based on the attention vector mechanism, which can automatically correlate the context of security events, extract the event sequences, and group the sequences with similar features into the same cluster, and the analysts only need to judge and dispose of the clusters, so as to achieve the purpose of enhancing the monitoring capability and improving the monitoring efficiency.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Guoliang Lu, Xue Jia, Shuqi Wang, and Hao Yu "Clustering method for security events based on attention mechanism", Proc. SPIE 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024), 1322415 (7 August 2024); https://doi.org/10.1117/12.3034874

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE