Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67597
Volume:
10 |
9 |
Sep 2026
Pages:
1-6
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.
Information Technology and Computer Science
D G Ruparel of Arts, Commerce And Science
Information Technology and Computer Science
D G Ruparel of Arts, Commerce And Science
Machine learning-based network intrusion detection systems often perform extremely well on standard test datasets. However, high accuracy on clean data does not necessarily mean that these models can withstand carefully designed input manipulation. In this study, we examine the robustness of three widely used classifiers, namely Random Forest, XGBoost, and a multilayer perceptron (MLP), using the InSDN dataset. The problem is treated as a binary classification task in which network traffic is categorized as either Normal or Attack. Before training the models, duplicate records were removed, while identifier and timestamp fields were excluded from the dataset. The remaining data was processed using training-only preprocessing, and the 40 features with the highest mutual information scores were selected for the experiments. The three classifiers were initially tested using an untouched test set to establish their performance under normal conditions. They were then evaluated against a controlled feature-space adversarial evasion procedure, where bounded directional perturbations were applied using normalized budgets of ε ∈ {0.01, 0.025, 0.05, 0.10}. The models achieved almost perfect results on the clean test set, with F1 scores of 99.9927% for Random Forest, 99.9952% for XGBoost, and 99.9855% for MLP. However, their performance changed considerably when adversarial perturbations were introduced. For example, with a positive perturbation direction at ε=0.01, Random Forest recorded an attack success rate (ASR) of 94.09%. XGBoost reached an ASR of 93.15% at ε=0.05, while MLP reached 87.78% at the same perturbation budget. At ε=0.10 in the positive direction, both Random Forest and MLP reached an ASR of 100%.
KEYWORDS
This study evaluated RF, XGBoost, and MLP on the InSDN dataset using a controlled feature-space adversarial evasion procedure. Although all three models achieved over 99.98% F1 on clean data, their performance dropped significantly under adversarial perturbations. RF reached 94.09% ASR at ε=0.01 and 100% at ε=0.10, while XGBoost and MLP reached 93.15% and 87.78% ASR at ε=0.05, respectively. MLP also reached 100% ASR at ε=0.10. These results show that high clean-test performance does not necessarily indicate adversarial robustness. The effect of an attack also depends on its strength and direction. This study is limited to an offline feature-space evaluation, while future work can examine packet-level attacks, feature constraints, adversarial training, model-aware attacks, and cross-dataset testing.
[1] D. Kreutz, F. M. V. Ramos, P. E. Veríssimo, C. E. Rothenberg, S. Azodolmolky, and S. Uhlig, “Software-defined networking: A comprehensive survey,” Proceedings of the IEEE, vol. 103, no. 1, pp. 14–76, 2015, doi: 10.1109/JPROC.2014.2371999. [2] M. Said Elsayed, N.-A. Le-Khac, and A. D. Jurcut, “InSDN: A novel SDN intrusion dataset,” IEEE Access, vol. 8, pp. 165263–165284, 2020, doi: 10.1109/ACCESS.2020.3022633. [3] O. Yurekten and M. Demirci, “SDN-based cyber defense: A survey,” Future Generation Computer Systems, vol. 115, pp. 126–142, 2021. [4] M. P. Singh, A. K. Pradhan, and S. K. Singh, “New-flow based DDoS attacks in SDN: Taxonomy, rationales, and research challenges,” Computer Communications, vol. 154, pp. 509–525, 2020, doi: 10.1016/j.comcom.2020.02.085. [5] O. S. Sahoo et al., “An early detection of low rate DDoS attack to SDN based data center networks using information distance metrics,” Future Generation Computer Systems, vol. 89, pp. 685–697, 2018, doi: 10.1016/j.future.2018.07.017. [6] A. Ahmed Bahashwan, M. Anbar, S. Manickam, T. A. Al-Amiedy, M. A. Aladaileh, and I. H. Hasbullah, “A systematic literature review on machine learning and deep learning approaches for detecting DDoS attacks in software-defined networking,” Sensors, vol. 23, no. 9, p. 4441, 2023, doi: 10.3390/s23094441. [7] E. A. Al Mandhari et al., “A systematic literature review on the accuracy of machine learning based DDoS detection techniques in Software Defined Networking,” Discover Computing, vol. 29, p. 147, 2026. [8] W. Wang, Y. Liu, Q. Meng, and Z. Chen, “DDoS attack detection and defense techniques in software defined networks: A survey,” Computer Science Review, vol. 60, p. 100921, 2026, doi: 10.1016/j.cosrev.2026.100921. [9] M. P. Novaes, L. F. Carvalho, J. Lloret, and M. L. Proença Jr., “Adversarial deep learning approach detection and defense against DDoS attacks in SDN environments,” Future Generation Computer Systems, vol. 125, pp. 156–167, 2021, doi: 10.1016/j.future.2021.06.047. [10] A. A. Aiken and S. Scott-Hayward, “Investigating adversarial attacks against network intrusion detection systems in SDNs,” in Proc. IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), 2019, doi: 10.1109/NFV-SDN47374.2019.9040101.
Publication Date
9/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
8
Total views since publication
PDF Downloads
12
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...