Abstract

The rising frequency of cyberattacks, especially those targeting critical infrastructure, highlights the urgent need for robust network intrusion detection systems (IDS) specifically designed for the internet of things (IoT). Security issues in IoT networks are particularly complex due to the large number of connected devices and the emergence of new, sophisticated threats. To address these challenges, this research proposes a hybrid IDS architecture that combines machine learning (ML) and neural network (NN) approaches, leveraging cascade backpropagation neural networks (CPBNN) and convolutional neural networks (CNN) to enhance IoT security. The proposed system is designed to identify vulnerabilities in IoT systems, including distributed denial of service (DDoS) attacks, while addressing specific challenges related to scalability and the inherent complexity of IoT networks. The methodology employs a dual-layered approach: CPBNN is used to detect anomalous traffic, focusing on identifying abnormal behaviors, while CNN distinguishes between different types of traffic to determine the nature of the identified anomalies. The proposed hybrid IDS is evaluated using the KDDTest-21 dataset and assessed based on performance metrics including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the hybrid IDS achieves an accuracy of 90% with the CNN model and 82% with the CPBNN model, confirming its effectiveness in detecting and mitigating IoT-specific security threats. These findings highlight the importance of integrating advanced ML techniques to safeguard IoT networks against evolving threats.

Keyword

Cascade backpropagation neural network (CPBNN), Convolutional neural network (CNN), KDDTest- 21, Distributed denial of service (DDoS) attacks, Intrusion detection system (IDS), IoT security.

Cite this article

.Hybrid IDS architecture for IoT security enhancing threat detection with CPBNN and CNN models. International Journal of Advanced Technology and Engineering Exploration. 2024;11(120):1579-1591. DOI:10.19101/IJATEE.2024.111100172

Refference

[1]Megantara AA, Ahmad T. A hybrid machine learning method for increasing the performance of network intrusion detection systems. Journal of Big Data. 2021; 8(1):142.

[2]Yonan JF, Zahra NA. Node intrusion tendency recognition using network level features based deep learning approach. Babylonian Journal of Networking. 2023; 2023:1-10.

[3]Abbood Z, Yonan JF. Driver drowsy and yawn system alert using deep cascade convolution neural network DCCNN. Iraqi Journal for Computer Science and Mathematics. 2023; 4(4):111-20.

[4]Liao H, Murah MZ, Hasan MK, Aman AH, Fang J, Hu X, et al. A survey of deep learning technologies for intrusion detection in internet of things. IEEE Access. 2024.

[5]Demedeiros K, Hendawi A, Alvarez M. A survey of AI-based anomaly detection in IoT and sensor networks. Sensors. 2023; 23(3):1-33.

[6]Markevych M, Dawson M. A review of enhancing intrusion detection systems for cybersecurity using artificial intelligence (AI). In international conference knowledge-based organization 2023 (pp. 30-7). Sciendo.

[7]Salman QS, Nsaif SM. Advancements in time series-based detection systems for distributed denial-of-service (ddos) attacks: a comprehensive review. Babylonian Journal of Networking. 2024; 2024:9-17.

[8]Sharma S, Yadav M, Chandan M. Explainable AI (XAI): bridging the gap between machine learning and human understanding. Res Militaris. 2020; 10(1):156-65.

[9]Otoum Y, Wan Y, Nayak A. Federated transfer learning-based ids for the internet of medical things (IOMT). In GLOBECOM workshops 2021 (pp. 1-6). IEEE.

[10]Mabrouk A. Innovative approach for optimized IOT security based on spatial network voronoï diagrams, network centrality, and ML-enabled blockchain. In blockchain and machine learning for IoT security (pp. 31-55). Chapman and Hall/CRC.

[11]Thirumalairaj A, Jeyakarthic M. Hybrid cuckoo search optimization based tuning scheme for deep neural network for intrusion detection systems in cloud environment. Journal of Research on the Lepidoptera. 2020; 51(2):209-24.

[12]Taulli T. Large language models: how generative AI understands language. In generative AI: how chatGPT and other AI tools will revolutionize business 2023 (pp. 93-125). Berkeley, CA: Apress.

[13]Tsimenidis S, Lagkas T, Rantos K. Deep learning in IoT intrusion detection. Journal of Network and Systems Management. 2022; 30(1):8.

[14]Nanjappan M, Pradeep K, Natesan G, Samydurai A, Premalatha G. DeepLG SecNet: utilizing deep LSTM and GRU with secure network for enhanced intrusion detection in IoT environments. Cluster Computing. 2024:1-3.

[15]Kumar GSC, Kumar RK, Kumar KPV, Sai NR, Brahmaiah M. Deep residual convolutional neural network: an efficient technique for intrusion detection system. Expert Systems with Applications. 2024; 238(4):121912.

[16]Mohamed D, Ismael O. Enhancement of an IoT hybrid intrusion detection system based on fog-to-cloud computing. Journal of Cloud Computing. 2023; 12(1):41.

[17]Manocchio LD, Layeghy S, Lo WW, Kulatilleke GK, Sarhan M, Portmann M. Flowtransformer: a transformer framework for flow-based network intrusion detection systems. Expert Systems with Applications. 2024; 241:122564.

[18]Hikal NA, Elgayar MM. Enhancing IoT botnets attack detection using machine learning-IDS and ensemble data preprocessing technique. In proceedings of ITAF internet of things-applications and future: 2019 (pp. 89-102). Singapore: Springer Singapore.

[19]Perumal G, Subburayalu G, Abbas Q, Naqi SM, Qureshi I. VBQ-Net: a novel vectorization-based boost quantized network model for maximizing the security level of IoT system to prevent intrusions. Systems. 2023; 11(8):1-25.

[20]Mahalingam A, Perumal G, Subburayalu G, Albathan M, Altameem A, Almakki RS, et al. ROAST-IoT: a novel range-optimized attention convolutional scattered technique for intrusion detection in IoT networks. Sensors. 2023; 23(19):1-29.

[21]Gueriani A, Kheddar H, Mazari AC. Deep reinforcement learning for intrusion detection in IoT: a survey. In international conference on electronics, energy and measurement 2023 (pp. 1-7). IEEE.

[22]Mohan RKR, Katiravan J. Dynamic trusted cross-layer IDS for secured communications in wireless networks using routing algorithm and FT-CNN. Journal of Intelligent & Fuzzy Systems. 2024:1-3.

[23]Bala S, Ahsan SM. Detecting DDoS attacks in software define networking: a machine learning based approach. In international conference on next-generation computing, IoT and machine learning 2023 (pp. 1-6). IEEE.

[24]Raimundo A, Pavia JP, Sebastião P, Postolache O. YOLOX-Ray: an efficient attention-based single-staged object detector tailored for industrial inspections. Sensors. 2023; 23(10):1-26.

[25]Alnifie KM, Kim C. Appraising the manifestation of optimism bias and its impact on human perception of cyber security: a meta analysis. Journal of Information Security. 2023; 14(2):93-110.

[26]Sharghivand N, Derakhshan F. Data security and privacy in industrial IoT. AI-Enabled Threat Detection and Security Analysis for Industrial IoT. 2021:21-39.

[27]Al-rubaye SA. Intrusion detection system in IoT networks using SVM-PSO classification. Masters Thesis, Institute of Graduate Education - Altınbaş University. 2022.

[28]https://www.kaggle.com/datasets/hassan06/nslkdd. Accessed 20 October 2024.

[29]Songa AV, Karri GR. Ensemble-RNN: a robust framework for DDoS detection in cloud environment. Majlesi Journal of Electrical Engineering. 2023; 17(4):31-44.

[30]Alashhab AA, Zahid MS, Muneer A, Abdullahi M. Low-rate DDoS attack detection using deep learning for SDN-enabled IoT networks. International Journal of Advanced Computer Science and Applications. 2022; 13(11).

[31]Haider S, Akhunzada A, Mustafa I, Patel TB, Fernandez A, Choo KK, et al. A deep CNN ensemble framework for efficient DDoS attack detection in software defined networks. IEEE Access. 2020; 8:53972-83.