Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62492
Volume:
10 |
5 |
May 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science and Engineering
Bharath Institute of Higher Education and Research, Chennai,India.
Department of Computer Science and Engineering
Bharath Institute of Higher Education and Research, Chennai,India.
Department of Computer Science and Engineering
Bharath Institute of Higher Education and Research, Chennai,India.
Department of Computer Science and Engineering
Bharath Institute of Higher Education and Research, Chennai,India.
The rapid growth of digital financial systems has significantly increased the exposure of financial organizations to various cyber threats, including fraud, phishing, malware, and unauthorized access. Traditional security mechanisms are often insufficient to detect sophisticated and evolving cyberattacks in real time. This paper proposes a machine learning-based cyber threat detection system designed to identify malicious activities in financial environments. The system utilizes historical cybersecurity data such as transaction records, user behavior, and network activity to train predictive models capable of detecting anomalies and potential threats. Various machine learning algorithms, including Logistic Regression, Random Forest, Support Vector Machine, and XGBoost, are implemented to analyze complex patterns in the data and classify activities as normal or malicious. The proposed system demonstrates high detection accuracy and robustness through effective data preprocessing, feature selection, and model training techniques. Performance evaluation using metrics such as accuracy, precision, recall, and F1-score indicates that the system can reliably detect cyber threats while minimizing false positives. The integration of the model into a real-time monitoring framework enables continuous surveillance of financial systems and early detection of security breaches. The results highlight the effectiveness of machine learning in enhancing cybersecurity and protecting sensitive financial data. This approach provides a scalable and intelligent solution for financial organizations to strengthen their defense mechanisms against evolving cyber threats.
KEYWORDS
A. System Deployment and Real-Time Monitoring The final stage of the proposed work involves deploying the trained model into a real-time cybersecurity monitoring system. The threat detection system can be integrated into a web-based dashboard or security platform that allows administrators to monitor system activity and detect threats instantly. Visualization tools such as graphs and alert dashboards can be used to display suspicious activities, attack trends, and system performance. This helps security teams quickly understand and respond to potential threats. Such a system supports financial institutions in strengthening their cybersecurity infrastructure and improving decision-making processes. Cyber threat levels can be represented using a risk scoring mechanism, where higher scores indicate a greater likelihood of malicious activity. This enables organizations to prioritize critical threats and take immediate action to protect sensitive financial data and maintain system integrity.
J. V. Zidek, W. Sun, and N. Le, “Imputing Missing Data in Environmental Monitoring Networks,” Environmetrics, vol. 11, no. 3, pp. 279–297, 2000. [2] T. M. Mitchell, Machine Learning. New York, NY, USA: McGraw-Hill, 1997. [3] C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006. [4] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016. [5] N. Sommer and V. Paxson, “Outside the Closed World: On Using Machine Learning for Network Intrusion Detection,” in Proc. IEEE Symp. Security Privacy, 2010, pp. 305–316. [6] G. Creech and J. Hu, “A Semantic Approach to Host-Based Intrusion Detection Systems Using Contiguous and Discontiguous System Call Patterns,” IEEE Trans. Comput., vol. 63, no. 4, pp. 807–819, 2014. [7] M. Tavallaee, E. Bagheri, W. Lu, and A. A. Ghorbani, “A Detailed Analysis of the KDD CUP 99 Data Set,” in Proc. IEEE Symp. Computational Intelligence for Security and Defense Applications, 2009, pp. 1–6. [8] A. L. Buczak and E. Guven, “A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection,” IEEE Commun. Surveys Tuts., vol. 18, no. 2, pp. 1153–1176, 2016. [9] S. Axelsson, “The Base-Rate Fallacy and Its Implications for the Difficulty of Intrusion Detection,” ACM Trans. Inf. Syst. Secur., vol. 3, no. 3, pp. 186–205, 2000. [10] J. D. Brutlag, “Aberrant Behavior Detection in Time Series for Network Monitoring,” in Proc. USENIX LISA, 2000, pp. 139–146. [11] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5– 32, 2001. [12] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 785– 794.
Publication Date
5/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...