An optimization method for enterprise user anomaly detection based on FCM

Yifei Huang; Xin Li; Chengming Zou

doi:10.1117/12.3032958

5 July 2024 An optimization method for enterprise user anomaly detection based on FCM

Yifei Huang, Xin Li, Chengming Zou

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318468 (2024) https://doi.org/10.1117/12.3032958
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

As businesses continue to expand and digitize, there is a surge in both internal and load data. However, internal data, which is one of the core assets of a company, is increasingly under severe security threats. More covert attacks characterized by long cycles, low frequency, and high stealth are bypassing traditional security detection methods, causing extensive damage to data. To address this, we propose an approach that integrates various types of data reflecting the baseline of user behavior, based on the correlation of users, entities, and behaviors. We extract several fundamental features that most effectively indicate user anomalies and combine the XGBoost feature selection strategy with the FCM clustering algorithm. By scoring anomalies, we can identify the users posing the highest risk of anomalies. The results demonstrate that the newly proposed anomaly detection algorithm achieves an accuracy rate of over 83.5% and a recall rate of over 86.7%.

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

Citation Download Citation

Yifei Huang, Xin Li, and Chengming Zou "An optimization method for enterprise user anomaly detection based on FCM", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318468 (5 July 2024); https://doi.org/10.1117/12.3032958

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

Includes PDF, HTML & Video, when available