Abstract
AbstractThe Internet of things (IoT) is an important technology that is highly beneficial in establishing smart items, connections and cities. However, there are worries regarding security and privacy vulnerabilities in IoT in which some emerge from numerous sources, including cyberattacks, unsecured networks, data, connections or communication. This paper provides an ensemble intrusion strategy based on Cyborg Intelligence (machine learning and biological intelligence) framework to boost security of IoT enabled networks utilized for network traffic of smart cities. To do this, multiple algorithms such Random Forest, Bayesian network (BN), C5.0, CART and Artificial Neural Network were investigated to determine their usefulness in identifying threats and attacks-botnets in IoT networks based on cyborg intelligence using the KDDcup99 dataset. The results reveal that the AdaBoost ensemble learning based on Cyborg Intelligence Intrusion Detection framework facilitates dissimilar network characteristics with the capacity to swiftly identify different botnet assaults efficiently. The suggested framework has obtained good accuracy, detection rate and a decreased false positive rate in comparison to other standard methodologies. The conclusion of this study would be a valuable complement to the efforts toward protecting IoT-powered networks and the accomplishment of safer smart cities.
Funder
Dirección General de Investigaciones of Universidad Santiago de Cali under
Publisher
Springer Science and Business Media LLC
Subject
Computer Networks and Communications,Software
Reference41 articles.
1. Onyema EM, Edeh CD, Gregory US, Edmond VU, Charles AC, Richard-Nnabu NE (2021) Cybersecurity awareness among undergraduate students in Enugu Nigeria. Int J Inform Sec Privacy Digital Forensic 5(1):34–42
2. Rockson KA, Michael A, Onyema EM (2020) Implementing morpheme-based compression security mechanism in distributed systems. Int J Innov Rese Dev 9(2):157–162
3. Kumar P et al (2021) PPSF: a privacy-preserving and secure framework using blockchain-based machine- learning for IoT-Driven smart Cities. IEEE Trans Netw Sci Eng 8(3):2326–2341. https://doi.org/10.1109/TNSE.2021.3089435
4. Alhakami W, Alharbi A, Bourouis S, Alroobaea R, Bouguila N (2019) Network anomaly intrusion detection using a nonparametric Bayesian approach and feature selection”. IEEE Access 7:52181–52190. https://doi.org/10.1109/ACCESS.2019.2912115
5. Ahmad I, Haq QEU, Imran M, Alassafi MO, Alghamdi RA (2022) An efficient network intrusion detection and classification system. Mathematics 10(3):1–15. https://doi.org/10.3390/math10030530
Cited by
28 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献