Utility Analysis about Log Data Anomaly Detection Based on Federated Learning
Logs that record system information are managed in anomaly detection, and more efficient anomaly detection methods have been proposed due to their increase in complexity and scale. Accordingly, deep learning models that automatically detect system anomalies through log data learning have been propos...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4495 |
| _version_ | 1797608339710935040 |
|---|---|
| author | Tae-Ho Shin Soo-Hyung Kim |
| author_facet | Tae-Ho Shin Soo-Hyung Kim |
| author_sort | Tae-Ho Shin |
| collection | DOAJ |
| description | Logs that record system information are managed in anomaly detection, and more efficient anomaly detection methods have been proposed due to their increase in complexity and scale. Accordingly, deep learning models that automatically detect system anomalies through log data learning have been proposed. However, in existing log anomaly detection models, user logs are collected from the central server system, exposing the data collection process to the risk of leaking sensitive information. A distributed learning method, federated learning, is a trend proposed for artificial intelligence learning regarding sensitive information because it guarantees the anonymity of the collected user data and collects only weights learned from each local server in the central server. In this paper, we executed an experiment regarding system log anomaly detection using federated learning. The results demonstrate the feasibility of applying federated learning in deep-learning-based system-log anomaly detection compared to the existing centralized learning method. Moreover, we present an efficient deep-learning model based on federated learning for system log anomaly detection. |
| first_indexed | 2024-03-11T05:42:03Z |
| format | Article |
| id | doaj.art-93f85b3a30bc45c590104657fb3563cd |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:42:03Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-93f85b3a30bc45c590104657fb3563cd2023-11-17T16:21:08ZengMDPI AGApplied Sciences2076-34172023-04-01137449510.3390/app13074495Utility Analysis about Log Data Anomaly Detection Based on Federated LearningTae-Ho Shin0Soo-Hyung Kim1Interdisciplinary Program of Information Security, Chonnam National University, Gwangju 61186, Republic of KoreaInterdisciplinary Program of Information Security, Chonnam National University, Gwangju 61186, Republic of KoreaLogs that record system information are managed in anomaly detection, and more efficient anomaly detection methods have been proposed due to their increase in complexity and scale. Accordingly, deep learning models that automatically detect system anomalies through log data learning have been proposed. However, in existing log anomaly detection models, user logs are collected from the central server system, exposing the data collection process to the risk of leaking sensitive information. A distributed learning method, federated learning, is a trend proposed for artificial intelligence learning regarding sensitive information because it guarantees the anonymity of the collected user data and collects only weights learned from each local server in the central server. In this paper, we executed an experiment regarding system log anomaly detection using federated learning. The results demonstrate the feasibility of applying federated learning in deep-learning-based system-log anomaly detection compared to the existing centralized learning method. Moreover, we present an efficient deep-learning model based on federated learning for system log anomaly detection.https://www.mdpi.com/2076-3417/13/7/4495federated learningdeep learninglog analysisanomaly detection |
| spellingShingle | Tae-Ho Shin Soo-Hyung Kim Utility Analysis about Log Data Anomaly Detection Based on Federated Learning Applied Sciences federated learning deep learning log analysis anomaly detection |
| title | Utility Analysis about Log Data Anomaly Detection Based on Federated Learning |
| title_full | Utility Analysis about Log Data Anomaly Detection Based on Federated Learning |
| title_fullStr | Utility Analysis about Log Data Anomaly Detection Based on Federated Learning |
| title_full_unstemmed | Utility Analysis about Log Data Anomaly Detection Based on Federated Learning |
| title_short | Utility Analysis about Log Data Anomaly Detection Based on Federated Learning |
| title_sort | utility analysis about log data anomaly detection based on federated learning |
| topic | federated learning deep learning log analysis anomaly detection |
| url | https://www.mdpi.com/2076-3417/13/7/4495 |
| work_keys_str_mv | AT taehoshin utilityanalysisaboutlogdataanomalydetectionbasedonfederatedlearning AT soohyungkim utilityanalysisaboutlogdataanomalydetectionbasedonfederatedlearning |