A hybrid cryptographic framework with machine learning-based anomaly detection for secure network traffic using UNSW-NB15
Swami Nisha Bhagirathswami.bhagirath@jaipur.manipal.eduDepartment of Computer ApplicationsManipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , Bindiya JainBindiya.jain@poornima.edu.inFaculty of Computer Science and EngineeringPoornima UniversityJaipur, Rajasthan, 303905, IndiaView full profile → , Pragya Singhspragyasingh@gmail.comSymbiosis Centre for Management Studies (Noida)Symbiosis International (Deemed University)Noida, Uttar Pradesh, 201301, IndiaView full profile → , Vaibhav Bhavnagarvaibhav.bhatnagar@jaipur.manipal.eduDepartment of Computer ApplicationsManipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile → , *Rajesh HandaCorresponding authorrajesh.handa@jaipur.manipal.eduCentre for Distance and Online Education (CDOE)Manipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-3091
- Pages:
- 4775–4786
Abstract
The advancement of technology is changing digital communication systems rapidly. The development of network topologies is equally growing. Both trends have led to an increase in the number of cyber threats. Intelligent and adaptive Network Intrusion Detection Systems (NIDS) have become more necessary to counter the growing threat of cyber-attacks that include zero-day exploits, polymorphic malware, and other malicious traffic patterns. Sophisticated attacks could go undetected in large-scale network environments. This paper proposed the possibility of using structured machine learning in intrusion detection by utilizing the UNSW-NB15 Dataset. The analysis involved comparison of five machine learning algorithms: Random Forest, Naive Bayes, Neural Network, Gradient Boosting, and Stochastic Gradient Descent. The Random Forest model achieved high accuracy.
Keywords
Subject Classifications
References
[1] A. D. Vibhute, M. Khan, C. H. Patil, S. V. Gaikwad, A. V. Mane, and K. K. Patel, “Network anomaly detection and performance evaluation of convolutional neural networks on UNSW-NB15 dataset,” Procedia Comput. Sci., vol. 235, pp. 2227–2236 (2024).
[2] A. Fathima, A. Khan, M. F. Uddin, M. M. Waris, S. Ahmad, C. Sanin, and E. Szczerbicki, “Performance evaluation and comparative analysis of machine learning models on the UNSW-NB15 dataset: A contemporary approach to cyber threat detection,” Cybern. Syst., vol. 56, no. 8, pp. 1160–1176 (2025).
[3] Y. F. Sallam, S. Abd El-Nabi, W. El-Shafai, H. E. D. H. Ahmed, A. Saleeb, N. A. El-Bahnasawy, and F. E. Abd El-Samie, “Efficient implementation of image representation, visual geometry group with 19 layers and residual network with 152 layers for intrusion detection from UNSW-NB15 dataset,” Security Privacy, vol. 6, no. 5, Art. no. e300 (2023).
[4] K. K. Ponniah and B. Retnaswamy, “A novel deep learning based intrusion detection system for the IoT-Cloud platform with blockchain and data encryption mechanisms,” J. Intell. Fuzzy Syst., vol. 45, no. 6, pp. 11707–11724 (2023).
[5] J. Jagannathan, S. G. Kumara, T. L. Narayana, and M. S. Alam, “Securing wireless communication using novel transfer learning for encryption in wireless networks,” ICTACT J. Commun. Technol., vol. 14, no. 3, p. 3005 (2023).
[6] M. Ali, S. Pervez, S. E. Hosseini, and M. K. Siddhu, “Evaluation and detection of cyberattack in IoT-based smart city networks using machine learning on the UNSW-NB15 dataset,” Int. J. Online Biomed. Eng., vol. 21, no. 2 (2025).
[7] A. Kumar, K. Guleria, R. Chauhan, and D. Upadhyay, “Advancing intrusion detection with machine learning: Insights from the UNSW-NB15 dataset,” in Proc. IEEE Int. Conf. Inf. Technol., Electron. Intell. Commun. Syst. (ICITEICS), pp. 1–5 (Jun. 2024).
[8] M. Shushlevska, D. Efnusheva, G. Jakimovski, and Z. Todorov, “Anomaly detection with various machine learning classification techniques over UNSW-NB15 dataset,” in Proc. 10th Int. Conf. Appl. Innov. IT (ICAIIT), Köthen, Germany, vol. 10, no. 1, pp. 21–27 (Mar. 2022), doi: 10.25673/76928.
[9] M. Manneh, P. Ansah, S. K. Tetarave, M. R. Mishra, and E. Kalaimannan, “A comparative analysis of random forest and support vector machine techniques on the UNSW-NB15 dataset,” in Proc. Int. Conf. Innovations Comput. Res., Cham, Switzerland: Springer Nature Switzerland, pp. 194–203 (2024).
[10] R. Sharma and S. Sobti, “A deep neural networks model for intrusion detection in UNSW-NB15 dataset,” in Proc. 4th Asian Conf. Innovation Technol. (ASIANCON), pp. 1–5 (Aug. 2024).
[11] R. Tahri, A. Jarrar, A. Lasbahani, and Y. Balouki, “A comparative study of machine learning algorithms on the UNSW-NB15 dataset,” ITM Web Conf., vol. 48, Art. no. 03002 (2022).
[12] N. Hassouneh and S. Al-Sharaeh, “Intrusion detection in IoT networks using LSTM deep learning models with the UNSW-NB15 dataset,” in Proc. Int. Conf. New Trends Comput. Sci. (ICTCS), pp. 263–269 (Apr. 2025).
[13] A. Al-Obaidi, A. A. Ibrahim, and A. M. Khaleel, “The effectiveness of deploying machine learning techniques in information security to detect nine attacks: UNSW-NB15 dataset as a case study,” Math. Model. Eng. Probl., vol. 10, no. 5 (2023).
[14] A. Thaljaoui, “Intelligent network intrusion detection system using optimized deep CNN-LSTM with UNSW-NB15,” Int. J. Inf. Technol., pp. 1–17 (2025).
[15] UNSW Canberra, “The UNSW-NB15 Dataset” (2021). [Online]. Available: https://research.unsw.edu.au/projects/unsw-nb15-dataset. [Accessed: Apr. 20, 2026].
[16] A. E. Curtis, T. A. Smith, B. A. Ziganshin, and J. A. Elefteriades, “The mystery of the Z-score,” Aorta, vol. 4, no. 4, pp. 124–130 (2016).
[17] M. W. Ahmad, J. Reynolds, and Y. Rezgui, “Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees,” J. Cleaner Prod., vol. 203, pp. 810–821 (2018).
[18] Y. Ma, C. Su, J. Liu, Z. Ren, C. Xu, and Y. Gao, “Predictions of nuclear charge radii and physical interpretations based on the naive Bayesian probability classifier,” Phys. Rev. C, vol. 101, no. 1, Art. no. 014304 (2020).
[19] A. D. Jagtap, K. Kawaguchi, and G. E. Karniadakis, “Adaptive activation functions accelerate convergence in deep and physics-informed neural networks,” J. Comput. Phys., vol. 404, Art. no. 109136 (2020).
[20] J. Guo, S. Yun, Y. Meng, N. He, D. Ye, Z. Zhao, L. Jia, and L. Yang, “Prediction of heating and cooling loads based on light gradient boosting machine algorithms,” Build. Environ., vol. 236, Art. no. 110252 (2023).
[21] R. C. Poonia, T. Singh, C. K. Rajashri, D. Mondal, and S. M. Patil, “Optimizing communication system security through comprehensive testing and intelligent network configurations,” J. Inf. Optim. Sci., vol. 47, no. 5-A, pp. 1709–1717 (2026), doi: 10.47974/JIOS-2261.
[22] M. Grandini, E. Bagli, and G. Visani, “Metrics for multi-class classification: An overview,” arXiv preprint arXiv:2008.05756 (2020).
[23] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, Art. no. 6 (2020).
