Abstract

Within the domain of cybersecurity, intrusion detection systems (IDS) represent a fundamental component for safeguarding digital infrastructures. Nevertheless, the pervasive issue of class imbalance in intrusion data remains a formidable challenge, adversely affecting the overall efficacy of such systems. To address this limitation, a novel framework termed coreset selection entropy generative adversarial network (CoreSEGAN) has been introduced. This advanced methodology incorporates an entropic filter in conjunction with a deep reinforcement learning (DRL) model to synthesize new samples specifically for minority classes, thereby mitigating the detrimental impact of class imbalance. CoreSEGAN functions by analyzing decision boundaries and generating additional instances for minority classes in the latent space. The effectiveness of this framework has been rigorously validated through experimental evaluations on four benchmark datasets, where it consistently outperforms prevailing state-of-the-art techniques and achieves an average accuracy of over 99% across all datasets. The results demonstrate significant improvements in classification accuracy, reduction of false alarms, and overall generalization across multiple datasets, establishing CoreSEGAN as an effective and scalable framework for intrusion detection in imbalanced environments.

Keywords

Intrusion detection system (IDS), Cybersecurity, coreset selection entropy generative adversarial network (CoreSEGAN), Entropy optimization, Generative adversarial network (GAN), Deep reinforcement learning (DRL).

Cite this article

Suma G, Suma S, Rukmani,. CoreSEGAN: coreset selection entropy generative adversarial network for IoT botnet detection.International Journal of Advanced Technology and Engineering Exploration.2025;12(131):1-18

References

[1] https://dataprot.net/statistics/iot-statistics/. Accessed 02 August 2024

[2] Zafar MH, Langås EF, Sanfilippo F. Exploring the synergies between collaborative robotics, digital twins, augmentation, and industry 5.0 for smart manufacturing: a state-of-the-art review. Robotics and Computer-Integrated Manufacturing. 2024; 89:1-29.

[3] Xames MD, Topcu TG. A systematic literature review of digital twin research for healthcare systems: research trends, gaps, and realization challenges. IEEE Access. 2024; 12:4099-126.

[4] Amru M, Kannan RJ, Ganesh EN, Muthumarilakshmi S, Padmanaban K, Jeyapriya J, et al. Network intrusion detection system by applying ensemble model for smart home. International Journal of Electrical and Computer Engineering. 2024; 14(3):3485-94.

[5] Huda NU, Ahmed I, Adnan M, Ali M, Naeem F. Experts and intelligent systems for smart homes’ transformation to sustainable smart cities: a comprehensive review. Expert Systems with Applications. 2024; 238:122380.

[6] Zhang Y, Liu Q. On IoT intrusion detection based on data augmentation for enhancing learning on unbalanced samples. Future Generation Computer Systems. 2022; 133:213-27.

[7] Xu L, Skoularidou M, Cuesta-infante A, Veeramachaneni K. Modeling tabular data using conditional gan. Advances in neural information processing systems 2019 (pp. 1-11).

[8] Bedi P, Gupta N, Jindal V. Siam-IDS: handling class imbalance problem in intrusion detection systems using siamese neural network. Procedia Computer Science. 2020; 171:780-9.

[9] Kuang L, Zulkernine M. An anomaly intrusion detection method using the CSI-KNN algorithm. In proceedings of the ACM symposium on applied computing 2008 (pp. 921-6). ACM.

[10] Tamilkodi R, Chandra PS, Balasankar V, Suseela D. A unique imbalanced network traffic-based algorithm related to deep learning and machine learning. In information system design: AI and ML applications: proceedings of eighth international conference on information system design and intelligent applications 2024 (pp. 473-84). Springer Nature.

[11] Konatham BR. A secure and efficient IIoT anomaly detection approach using a hybrid deep learning technique. Master Thesis, Gandhi Institute of Technology and Management, India. 2018.

[12] Zhang H, Huang L, Wu CQ, Li Z. An effective convolutional neural network based on SMOTE and gaussian mixture model for intrusion detection in imbalanced dataset. Computer Networks. 2020; 177:107315.

[13] Widodo AO, Setiawan B, Indraswari R. Machine learning-based intrusion detection on multi-class imbalanced dataset using SMOTE. Procedia Computer Science. 2024; 234:578-83.

[14] Vijayakumar DS, Ganapathy S. Multistage ensembled classifier for wireless intrusion detection system. Wireless Personal Communications. 2022; 122(1):645-68.

[15] Sayegh HR, Dong W, Al-madani AM. Enhanced intrusion detection with LSTM-based model, feature selection, and SMOTE for imbalanced data. Applied Sciences. 2024; 14(2):1-20.

[16] Eid AM, Soudan B, Nassif AB, Injadat M. Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing. Neural Computing and Applications. 2024; 36(24):14643-59.

[17] Talukder MA, Islam MM, Uddin MA, Hasan KF, Sharmin S, Alyami SA, et al. Machine learning-based network intrusion detection for big and imbalanced data using oversampling, stacking feature embedding and feature extraction. Journal of Big Data. 2024; 11(1):1-44.

[18] Liu J, Gao Y, Hu F. A fast network intrusion detection system using adaptive synthetic oversampling and LightGBM. Computers & Security. 2021; 106:102289.

[19] Huang S, Lei K. IGAN-IDS: an imbalanced generative adversarial network towards intrusion detection system in ad-hoc networks. Ad Hoc Networks. 2020; 105:102177.

[20] Ding H, Chen L, Dong L, Fu Z, Cui X. Imbalanced data classification: a KNN and generative adversarial networks-based hybrid approach for intrusion detection. Future Generation Computer Systems. 2022; 131:240-54.

[21] Alqarni AA, El-alfy ES. Improving intrusion detection for imbalanced network traffic using generative deep learning. International Journal of Advanced Computer Science and Applications. 2022; 13(4):1-10.

[22] Babu KS, Rao YN. MCGAN: modified conditional generative adversarial network (MCGAN) for class imbalance problems in network intrusion detection system. Applied Sciences. 2023; 13(4):1-13.

[23] Chapaneri R, Shah S. Enhanced detection of imbalanced malicious network traffic with regularized generative adversarial networks. Journal of Network and Computer Applications. 2022; 202:103368.

[24] Rahman MA, Shahrier H. Towards developing generative adversarial networks based robust intrusion detection systems for imbalanced dataset using Hadoop-PySpark. In the international conference on innovations in computing research 2024 (pp. 449-63). Cham: Springer Nature Switzerland.

[25] Zhou S, Wang L, Yang J, Zhan P. Sitd: insider threat detection using siamese architecture on imbalanced data. In 25th international conference on computer supported cooperative work in design (CSCWD) 2022 (pp. 245-50). IEEE.

[26] https://www.kaggle.com/datasets/mkashifn/nbaiot-dataset. Accessed 11 August 2024.

[27] Goodfellow IJ, Pouget-abadie J, Mirza M, Xu B, Warde-farley D, Ozair S, et al. Generative adversarial nets. Advances in neural information processing systems 2014 (pp. 1-9).

[28] https://www.unb.ca/cic/datasets/ids.html. Accessed 11 August 2024.

[29] https://www.unb.ca/cic/datasets/ids-2017.html. Accessed 11 August 2024.

[30] https://www.unb.ca/cic/datasets/ids-2018.html. Accessed 11 August 2024.

[31] Apruzzese G, Andreolini M, Marchetti M, Venturi A, Colajanni M. Deep reinforcement adversarial learning against botnet evasion attacks. IEEE Transactions on Network and Service Management. 2020; 17(4):1975-87.

[32] Mao Z, Fang Z, Li M, Fan Y. EvadeRL: evading PDF malware classifiers with deep reinforcement learning. Security and Communication Networks. 2022; 2022(1):1-14.