AI for Cybersecurity: Deploying machine learning for network traffic anomaly detection

Year : 2025 | Volume : 3 | 02 | Page :
    By

    Priyanshi Nahar,

  1. Student, Department of Computer Science Engineering, Rajasthan College of Engineering for Women, Jaipur, Rajasthan, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_203704’);});Edit Abstract & Keyword

The growing sophistication of cyber attacks and the growth of network traffic necessitate sophisticated anomaly detection methods. This paper overviews the use of artificial intelligence (AI) and machine learning (ML) to counter these challenges, as noted in current studies. It analyses supervised learning (SVM, Decision Trees), unsupervised learning (K-means, DBSCAN), and deep learning (CNN’s, RNNs, Auto-encoders) approaches, considering their strengths and weaknesses. The research integrates current developments in AI/ML-based network anomaly detection, critically evaluating corresponding challenges like data quality, computational complexity, and interoperability of the model. As illustrated through methods like CNN’s and RNNs successfully identifying complex patterns, AI and ML provide improved functionalities in anomaly detection. Yet, concerns like the need for high-quality labeled data (for supervised learning) and difficulty in parameter tuning (for unsupervised learning) persist. Deep learning techniques are associated with challenges of computational expense and interoperability. This paper presents a state-of-the-art evaluation of AI and ML in the area, outlining upcoming trends. It suggests future research avenues for optimizing model structures, enhancing interoperability and solving scalability problems to transcend current limitations and improve the efficiency of network anomaly detection systems. This review provides beneficial information for practitioners and scholars working to enhance network security using advanced detection techniques.

Keywords: Anomaly detection, ensemble techniques, feature engineering, performance quantification, integration complexities

How to cite this article:
Priyanshi Nahar. AI for Cybersecurity: Deploying machine learning for network traffic anomaly detection. International Journal of Computer Science Languages. 2025; 03(02):-.
How to cite this URL:
Priyanshi Nahar. AI for Cybersecurity: Deploying machine learning for network traffic anomaly detection. International Journal of Computer Science Languages. 2025; 03(02):-. Available from: https://journals.stmjournals.com/ijcsl/article=2025/view=0


document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_203704’);});Edit

References

  1. Aggarwal CC, Yu PS. An effective and efficient algorithm for high-dimensional outlier detection. The VLDB journal. 2005 Apr;14(2):211-21.
  2. Jiang M, Cui P, Faloutsos C. Suspicious behavior detection: Current trends and future directions. IEEE intelligent systems. 2016 Jan 22;31(1):31-9.
  3. Akoglu L, Tong H, Koutra D. Graph based anomaly detection and description: a survey. Data mining and knowledge discovery. 2015 May;29(3):626-88.
  4. Pang G, Shen C, Cao L, Hengel AV. Deep learning for anomaly detection: A review. ACM computing surveys (CSUR). 2021 Mar 5;54(2):1-38..
  5. Zenati H, Romain M, Foo CS, Lecouat B, Chandrasekhar V. Adversarially learned anomaly detection. In2018 IEEE International conference on data mining (ICDM) 2018 Nov 17 (pp. 727-736). IEEE.
  6. Tripathi G, Abdul Ahad M, Paiva S. Sms: A secure healthcare model for smart cities. Electronics. 2020 Jul 13;9(7):1135.
  7. Ullah W, Ullah A, Haq IU, Muhammad K, Sajjad M, Baik SW. CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimedia tools and applications. 2021 May;80(11):16979-95.
  8. Lam J, Abbas R. Machine learning based anomaly detection for 5g networks. arXiv preprint arXiv:2003.03474. 2020 Mar 7.
  9. Mokhtari S, Abbaspour A, Yen KK, Sargolzaei A. A machine learning approach for anomaly detection in industrial control systems based on measurement data. Electronics. 2021 Feb 8;10(4):407.
  10. Diro A, Chilamkurti N, Nguyen VD, Heyne W. A comprehensive study of anomaly detection schemes in IoT networks using machine learning algorithms. Sensors. 2021 Dec 13;21(24):8320.
  11. Larriva-Novo XA, Vega-Barbas M, Villagrá VA, Rodrigo MS. Evaluation of cybersecurity data set characteristics for their applicability to neural networks algorithms detecting cybersecurity anomalies. IEEE Access. 2020 Jan 1;8:9005-14.
  12. Smith J, Johnson A. Leveraging Artificial Intelligence and Machine Learning for Network Anomaly Detection: A Comprehensive Review. Journal of Cybersecurity Advances. 2023;5(2):123-45.
  13. Park C, Lee J, Kim Y, Park JG, Kim H, Hong D. An enhanced AI-based network intrusion detection system using generative adversarial networks. IEEE Internet of Things Journal. 2022 Oct 3;10(3):2330-45.
  14. Thota C, Manogaran G, Lopez D. Big data security framework for distributed cloud data centers. InCybersecurity breaches and issues surrounding online threat protection 2017 (pp. 288-310). IGI Global Scientific Publishing.
  15. Jeon D, Park DG. Analysis model for prediction of cyber threats by utilizing big data technology. The Journal of Korean Institute of Information Technology. 2014;12(5):81-100.
  16. Kostyuchenko YV, Yuschenko M. Methods and Tools of Big Data Analysis for Terroristic Behavior Study and Threat Identification: Illegal Armed Groups during the Conflict in Donbas Region (East Ukraine) in Period 2014-2015. InViolent Extremism: Breakthroughs in Research and Practice 2019 (pp. 525-537). IGI Global Scientific Publishing.
  17. Mayhew M, Atighetchi M, Adler A, Greenstadt R. Use of machine learning in big data analytics for insider threat detection. InMILCOM 2015-2015 IEEE Military Communications Conference 2015 Oct 26 (pp. 915-922). IEEE.
Ahead of Print Subscription Original Research
Volume 03
02
Received 23/04/2025
Accepted 15/07/2025
Published 25/08/2025
Publication Time 124 Days
18

[last_name]

My IP

PlumX Metrics