International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | LogSentinel: An Automated Hybrid System for Systematic Log Classification and Threat Identification |
|---|---|
| ABSTRACT | Modern computing systems rely on logs to monitoring and security. Due to an increase in volumes of logs and an increased level of complexity, logs need to be analyzed manually which will lead to inefficiencies and errors. Rule-based methods are difficult to apply to unstructured and dynamic log data. Therefore, the purpose of this research paper is to develop LogSentinel as a hybrid system that uses both machine learning and natural language processing (NLP) to automatically classify log entries and detect potential cyber threats. LogSentinel has two primary classifications of log data. First, it classifies log entries quickly using regular expression to find specific patterns. Second, LogSentinel identifies patterns in semi-structured log data with machine learning algorithms. In addition to identifying patterns in log data, LogSentinel applies NLP methods to interpret ambiguity or complexities in the content of log entries. Lastly, LogSentinel detects brute force attacks through identifying repeat failures in login attempts. The input into LogSentinel is log data that is formatted as comma separated value (CSV), and the output from LogSentinel is formatted as structured Excel reports that allow users to easily interpret the results of their analysis. LogSentinel provides several benefits compared to traditional log analysis methods. These include improved accuracy of classification, better flexibility in handling multiple types of log formats and reduced labor associated with manual analysis. Furthermore, the authors demonstrate the effectiveness of LogSentinel’s performance in applying its functionality to cybersecurity monitoring and automated system management applications. |
| AUTHOR | JAY PANCHAL, SWEETY PATEL UG Student, Dept. of C.S.E, Parul Institute of Technology, Parul University, Vadodara, Gujarat, India Assistant Professor, Dept. of C.S.E, Parul Institute of Technology, Parul University, Vadodara, Gujarat, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404034 |
| pdf/34_LogSentinel An Automated Hybrid System for Systematic Log Classification and Threat Identification.pdf | |
| KEYWORDS | |
| References | 1. Anfeng Peng, Ajesh K. Chathoth, Stephen Lee, “Log Anomaly Detection with Large Language Models via Knowledge-Enriched Fusion,” arXiv preprint arXiv:2512.11997, 2025. 2. Wei Guan, Jian Cao, Shiyou Qian, Jianqi Gao, Chun Ouyang, “LogLLM: Log-based Anomaly Detection Using Large Language Models,” arXiv preprint arXiv:2411.08561, 2024. 3. Max Landauer, Sebastian Onder, Florian Skopik, Markus Wurzenberger, “Deep Learning for Anomaly Detection in Log Data: A Survey,” Machine Learning with Applications, vol. 12, 100470, 2023. 4. Viktor Beck, Max Landauer, Markus Wurzenberger, Florian Skopik, Andreas Rauber, “System Log Parsing with Large Language Models: A Review,” arXiv preprint arXiv:2504.04877, 2025. 5. Fatemeh Hadadi, Qinghua Xu, Domenico Bianculli, Lionel C. Briand, “LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs,” ACM Transactions on Software Engineering and Methodology, 2025. 6. Yinang Gao, Tongyi Luo, Kai Huang, et al., “LogLAA: An Adaptive Integrated Log Anomaly Analysis Framework,” Cybersecurity, vol. 9, 141, 2026. 7. Zanis Ali Khan, Donghwan Shin, Domenico Bianculli, Lionel C. Briand, “The Impact of Log Parsing on Deep Learning-based Anomaly Detection,” Empirical Software Engineering, vol. 29, 139, 2024. 8. Leeladhar Chourasiya, Sushma Khatri, U.K. Lilhore, et al., “Advanced System Log Analyzer for Anomaly Detection and Cyber Forensic Investigations using LSTM and Transformer Networks,” Journal of Cloud Computing, vol. 14, 60, 2025. 9. Musaad Alzahrani, “Investigating the Impact of Log-Sequence Embeddings on Anomaly Detection: A Systematic Study,” Information, vol. 17, no. 3, 228, 2026. 10. Shenglin Zhang, Ziang Chen, Zijing Que, et al., “LogPurge: Log Data Purification for Anomaly Detection via Rule-Enhanced Filtering,” arXiv preprint arXiv:2511.14062, 2025. 11. Junjie Huang, Zhihan Jiang, Zhuangbin Chen, Michael R. Lyu, “ULog: Unsupervised Log Parsing with LLMs through Log Contrastive Units,” arXiv preprint arXiv:2406.07174, 2024. 12. Jonathan Pan, Swee Liang Wong, Yidi Yuan, “RAGLog: Log Anomaly Detection using Retrieval-Augmented Generation,” arXiv preprint arXiv:2311.05261, 2023. 13. Lingzhe Zhang, Tong Jia, Mengxi Jia, Yifan Wu, Hongyi Liu, Ying Li, “XRAGLog: A Resource-Efficient Context-Aware Log Anomaly Detection Method Using Retrieval-Augmented Generation,” 2024. |
