Optimized common features selection and deep-autoencoder (OCFSDA) for lightweight intrusion detection in Internet of things
Pages 2559 - 2581
Abstract
Embedded systems, including the Internet of things (IoT), play a crucial role in the functioning of critical infrastructure. However, these devices face significant challenges such as memory footprint, technical challenges, privacy concerns, performance trade-offs and vulnerability to cyber-attacks. One approach to address these concerns is minimising computational overhead and adopting lightweight intrusion detection techniques. In this study, we propose a highly efficient model called optimized common features selection and deep-autoencoder (OCFSDA) for lightweight intrusion detection in IoT environments. The proposed OCFSDA model incorporates feature selection, data compression, pruning, and deparameterization. We deployed the model on a Raspberry Pi4 using the TFLite interpreter by leveraging optimisation and inferencing with semi-supervised learning. Using the MQTT-IoT-IDS2020 and CIC-IDS2017 datasets, our experimental results demonstrate a remarkable reduction in the computation cost in terms of time and memory use. Notably, the model achieved an overall average accuracies of 99% and 97%, along with comparable performance on other important metrics such as precision, recall, and F1-score. Moreover, the model accomplished the classification tasks within 0.30 and 0.12 s using only 2KB of memory.
References
[1]
Abdel-Basset M, Hawash H, Chakrabortty RK, and Ryan MJ Semi-supervised spatiotemporal deep learning for intrusions detection in IoT networks IEEE Internet Things J. 2021 8 15 12251-12265
[2]
Abdullah M, Alshannaq A, Balamash A, and Almabdy S Enhanced intrusion detection system using feature selection method and ensemble learning algorithms Int. J. Comput. Sci. Inf. Secur. (IJCSIS) 2018 16 2 48-55
[3]
Aghakhani, H., Meng, D., Wang, Y.X., Kruegel, C., Vigna, G.: Bullseye polytope: a scalable clean-label poisoning attack with improved transferability. In: 2021 IEEE European Symposium on Security and Privacy (EuroS &P). IEEE, pp. 159–178 (2021)
[4]
Amrita KKR A hybrid intrusion detection system: integrating hybrid feature selection approach with heterogeneous ensemble of intelligent classifiers Int. J. Netw. Secur. 2018 20 1 41-55
[5]
Azhagusundari B, Thanamani AS, et al. Feature selection based on information gain Int. J. Innov. Technol. Explor. Eng. (IJITEE) 2013 2 2 18-21
[6]
Baldi, P.: Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning. JMLR Workshop and Conference Proceedings, pp. 37–49 (2012)
[7]
Boppana TK and Bagade P GAN-AE: an unsupervised intrusion detection system for MQTT networks Eng. Appl. Artif. Intell. 2023 119
[8]
Borgohain, T., Kumar, U., Sanyal, S.: Survey of security and privacy issues of internet of things. arXiv preprint arXiv:1501.02211 (2015)
[9]
Chen Y, Wang S, Zhao Q, and Sun G Detection of multivariate geochemical anomalies using the bat-optimized isolation forest and bat-optimized elliptic envelope models J. Earth Sci. 2021 32 2 415-426
[10]
Choi, S.K., Yang, C.H., Kwak, J.: System hardening and security monitoring for IoT devices to mitigate IoT security vulnerabilities and threats. KSII Trans. Internet Inf. Syst. 12(2) (2018)
[11]
Ciklabakkal, E., Donmez, A., Erdemir, M., Suren, E., Yilmaz, M.K., Angin, P.: ARTEMIS: An intrusion detection system for MQTT attacks in internet of things. In: 2019 38th Symposium on Reliable Distributed Systems (SRDS). IEEE (2019).
[12]
Halim Z, Yousaf MN, Waqas M, Sulaiman M, Abbas G, Hussain M, Ahmad I, and Hanif M An effective genetic algorithm-based feature selection method for intrusion detection systems Comput. Secur. 2021 110
[13]
Hanafi, A.V., Ghaffari, A., Rezaei, H., Valipour, A., arasteh, B.: Intrusion detection in internet of things using improved binary golden jackal optimization algorithm and LSTM. Cluster Comput. 1–18 (2023)
[14]
Hindy, H., Tachtatzis, C., Atkinson, R., Bayne, E., Bellekens, X.: Mqtt-iot-ids2020: Mqtt internet of things intrusion detection dataset. IEEE Dataport (2020)
[15]
Hoque N, Singh M, and Bhattacharyya DK EFS-MI: an ensemble feature selection method for classification Complex Intell. Syst. 2018 4 2 105-118
[16]
Idrissi I, Moussaoui O, and Azizi M A lightweight optimized deep learning-based host-intrusion detection system deployed on the edge for IoT Int. J. Comput. Digital Syst. 2022 11 1 209-216
[17]
Ito Y Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory Neural Netw. 1991 4 3 385-394
[18]
Jaafar, F., Malik, Y., Serre, J., Wang, H., Wang, T.: Lightweight intrusion detection in MQTT based sensor network. In: 2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE (2022).
[19]
Jan SU, Ahmed S, Shakhov V, and Koo I Toward a lightweight intrusion detection system for the internet of things IEEE Access 2019 7 42450-42471
[20]
Jaw E and Wang X Feature selection and ensemble-based intrusion detection system: an efficient and comprehensive approach Symmetry 2021 13 10 1764
[21]
Kim S, Hwang C, and Lee T Anomaly based unknown intrusion detection in endpoint environments Electronics 2020 9 6 1022
[22]
Lahasan B and Samma H Optimized deep autoencoder model for internet of things intruder detection IEEE Access 2022 10 8434-8448
[23]
Le QV et al. A tutorial on deep learning part 2: Autoencoders, convolutional neural networks and recurrent neural networks Google Brain 2015 20 1-20
[24]
Lelewer DA and Hirschberg DS Data compression ACM Comput. Surv. (CSUR) 1987 19 3 261-296
[25]
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)
[26]
Li, J.: Research on intrusion detect system of internet of things based on deep learning. In: 2022 International Conference on Machine Learning and Knowledge Engineering (MLKE), pp. 55–58. IEEE (2022)
[27]
Li X, Chen W, Zhang Q, and Wu L Building auto-encoder intrusion detection system based on random forest feature selection Comput. Secur. 2020 95
[28]
Li Y, Qin T, Huang Y, Lan J, Liang Z, and Geng T HDFEF: a hierarchical and dynamic feature extraction framework for intrusion detection systems Comput. Secur. 2022 121
[29]
Li Y, Wang JL, Tian ZH, Lu TB, and Young C Building lightweight intrusion detection system using wrapper-based feature selection mechanisms Comput. Secur. 2009 28 6 466-475
[30]
Liang, Y.: Efficient temporal compression in wireless sensor networks. In: 2011 IEEE 36th Conference on Local Computer Networks, pp. 466–474. IEEE (2011)
[31]
Manek AS, Shenoy PD, and Mohan MC Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier World Wide Web 2017 20 135-154
[32]
Mendonca RV, Silva JC, Rosa RL, Saadi M, Rodriguez DZ, and Farouk A A lightweight intelligent intrusion detection system for industrial internet of things using deep learning algorithms Expert. Syst. 2022 39 5
[33]
Moukhafi M, El Yassini K, and Bri S A novel hybrid GA and SVM with PSO feature selection for intrusion detection system Int. J. Adv. Sci. Res. Eng. 2018 4 5 129-134
[34]
Mushtaq E, Zameer A, Umer M, and Abbasi AA A two-stage intrusion detection system with auto-encoder and LSTMs Appl. Soft Comput. 2022 121
[35]
Neisse, R., Baldini, G., Steri, G., Ahmad, A., Fourneret, E., Legeard, B.: Improving internet of things device certification with policy-based management. In: 2017 Global Internet of Things Summit (GIoTS), pp. 1–6. IEEE (2017)
[36]
Neumann U, Riemenschneider M, Sowa JP, Baars T, Kälsch J, Canbay A, and Heider D Compensation of feature selection biases accompanied with improved predictive performance for binary classification by using a novel ensemble feature selection approach BioData Mining 2016 9 1 1-14
[37]
Nguyen BH, Xue B, and Zhang M A survey on swarm intelligence approaches to feature selection in data mining Swarm Evol. Comput. 2020 54
[38]
Nguyen XH, Nguyen XD, Huynh HH, and Le KH Realguard: a lightweight network intrusion detection system for IoT gateways Sensors 2022 22 2 432
[39]
Okey OD, Melgarejo DC, Saadi M, Rosa RL, Kleinschmidt JH, and Rodríguez DZ Transfer learning approach to ids on cloud IoT devices using optimized CNN IEEE Access 2023 11 1023-1038
[40]
Osanaiye O, Ogundile O, Aina F, and Periola A Feature selection for intrusion detection system in a cluster-based heterogeneous wireless sensor network Facta Universitatis Ser. Electron. Energet. 2019 32 2 315-330
[41]
Otokwala, U.J., Petrovski, A., Kotenko, I.V.: Enhancing intrusion detection through data perturbation augmentation strategy, Unpublished (2024)
[42]
Paudice, A., Muñoz-González, L., Lupu, E.C.: Label sanitization against label flipping poisoning attacks. In: ECML PKDD 2018 Workshops: Nemesis 2018, UrbReas 2018, SoGood 2018, IWAISe 2018, and Green Data Mining 2018, Dublin, Ireland, September 10–14, 2018, Proceedings 18, pp. 5–15. Springer, Berlin (2019)
[43]
Peri, N., Gupta, N., Huang, W.R., Fowl, L., Zhu, C., Feizi, S., Goldstein, T., Dickerson, J.P.: Deep k-nn defense against clean-label data poisoning attacks. In: Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16, pp. 55–70. Springer, Berlin (2020)
[44]
Perumal G, Subburayalu G, Abbas Q, Naqi SM, and 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 8 436
[45]
Rachburee, N., Punlumjeak, W.: A comparison of feature selection approach between greedy, IG-ratio, chi-square, and MRMR in educational mining. In: 2015 7th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 420–424. IEEE (2015)
[46]
Rizvi, S., Scanlon, M., McGibney, J., Sheppard, J.: Deep learning based network intrusion detection system for resource-constrained environments. In: International Conference on Digital Forensics and Cyber Crime, pp. 355–367. Springer, Berlin (2022)
[47]
Rodríguez, D., Ruiz, R., Cuadrado-Gallego, J., Aguilar-Ruiz, J.: Detecting fault modules applying feature selection to classifiers. In: 2007 IEEE International Conference on Information Reuse and Integration, pp. 667–672. IEEE (2007)
[48]
Roesch, M., et al.: Snort: Lightweight intrusion detection for networks. In: Lisa, vol. 99, pp. 229–238 (1999)
[49]
Roy S, Li J, Choi BJ, and Bai Y A lightweight supervised intrusion detection mechanism for IoT networks Futur. Gener. Comput. Syst. 2022 127 276-285
[50]
Sandri M and Zuccolotto P A bias correction algorithm for the gini variable importance measure in classification trees J. Comput. Graph. Stat. 2008 17 3 611-628
[51]
Sayood K Introduction to Data Compression 2017 Burlington Morgan Kaufmann
[52]
Sharafaldin I, Lashkari AH, and Ghorbani AA Toward generating a new intrusion detection dataset and intrusion traffic characterization ICISSp 2018 1 108-116
[53]
Sharmila, B., Nagapadma, R.: QAE-IDS: DDoS anomaly detection in IoT devices using post-quantization training. Smart Sci. 1–16 (2023)
[54]
Sharmila B and Nagapadma R Quantized autoencoder (QAE) intrusion detection system for anomaly detection in resource-constrained IoT devices using rt-iot2022 dataset Cybersecurity 2023 6 1 41
[55]
Shone N, Ngoc TN, Phai VD, and Shi Q A deep learning approach to network intrusion detection IEEE Trans. Emerging Top. Comput. Intell. 2018 2 1 41-50
[56]
Siddharthan H, Deepa T, and Chandhar P SENMQTT-set: an intelligent intrusion detection in IoT-MQTT networks using ensemble multi cascade features IEEE Access 2022 10 33095-33110
[57]
Soe, Y.N., Feng, Y., Santosa, P.I., Hartanto, R., Sakurai, K.: Implementing lightweight IoT-IDS on raspberry PI using correlation-based feature selection and its performance evaluation. In: Advanced Information Networking and Applications: Proceedings of the 33rd International Conference on Advanced Information Networking and Applications (AINA-2019), vol 33, pp 458–469. Springer, Berlin (2020)
[58]
Subbiah S, Anbananthen KSM, Thangaraj S, Kannan S, and Chelliah D Intrusion detection technique in wireless sensor network using grid search random forest with boruta feature selection algorithm J. Commun. Netw. 2022 24 2 264-273
[59]
Tao P, Sun Z, and Sun Z An improved intrusion detection algorithm based on GA and SVM IEEE Access 2018 6 13624-13631
[60]
Van Der Maaten, L., Postma, E., Van den Herik, J., et al.: Dimensionality reduction: a comparative. J. Mach. Learn. Res. 10(66–71), 13 (2009)
[61]
Wang J, Xu J, Zhao C, Peng Y, and Wang H An ensemble feature selection method for high-dimensional data based on sort aggregation Syst. Sci. Control Eng. 2019 7 2 32-39
[62]
Wang Z, Chen H, Yang S, Luo X, Li D, and Wang J A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization PeerJ Comput. Sci. 2023 9
[63]
Wang Z, Li Z, He D, and Chan S A lightweight approach for network intrusion detection in industrial cyber-physical systems based on knowledge distillation and deep metric learning Expert Syst. Appl. 2022 206
[64]
Xiao F, Honma Y, and Kono T A simple algebraic interface capturing scheme using hyperbolic tangent function Int. J. Numer. Methods Fluids 2005 48 9 1023-1040
[65]
Xu, Y., Tang, Y., Yang, Q.: Deep learning for IoT intrusion detection based on LSTMs-AE. In: Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture, pp 64–68 (2020)
[66]
Zakariyya I, Kalutarage H, and Al-Kadri MO Towards a robust, effective and resource efficient machine learning technique for IoT security monitoring Comput. Secur. 2023 133
[67]
Zebari R, Abdulazeez A, Zeebaree D, Zebari D, and Saeed J A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction J. Appl. Sci. Technol. Trends 2020 1 2 56-70
[68]
Zeng D, Wu Z, Ding C, Ren Z, Yang Q, and Xie S Labeled-robust regression: simultaneous data recovery and classification IEEE Trans. Cybernet. 2020 52 6 5026-5039
[69]
Zhao R, Gui G, Xue Z, Yin J, Ohtsuki T, Adebisi B, and Gacanin H A novel intrusion detection method based on lightweight neural network for internet of things IEEE Internet Things J. 2021 9 12 9960-9972
Recommendations
A Generalized Lightweight Intrusion Detection Model With Unified Feature Selection for Internet of Things Networks
ABSTRACTThe applicability of the Internet of Things (IoT) cutting across different domains has resulted in newer “things” acquiring IP connectivity. These things, technically known as IoT devices, are vulnerable to diverse security threats. Consequently,...
In this paper, we present a novel lightweight intrusion detection model for Internet of Things networks (LIDM‐IoT) with a unified feature selection strategy. The proposed model, which uses the records of only a single attack type using XGBoost algorithm, ...
A novel intrusion detection system for internet of things devices and data
AbstractAs we enter the new age of the Internet of Things (IoT) and wearable gadgets, sensors, and embedded devices are extensively used for data aggregation and its transmission. The extent of the data processed by IoT networks makes it vulnerable to ...
Collaborative device-level botnet detection for internet of things
Highlights- A review of the state-of-the-art device-level intrusion detection approaches.
- A detailed analysis of existing botnet datasets and their features to support evaluation of IDS.
- A novel trustworthy botnet detection framework for ...
AbstractCyber attacks on the Internet of Things (IoT) have seen a significant increase in recent years. This is primarily due to the widespread adoption and prevalence of IoT within domestic and critical national infrastructures, as well as inherent ...
Comments
Information & Contributors
Information
Published In
© The Author(s) 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 30 April 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 18 Jan 2025