Deep Learning under Attack in IoT Networks: A Review of Cyberattack Concepts and Defense Strategies
Keywords:
Adversarial attacks, Cyber-attack, Cyber security, IoT attack, Machine learning security, Proactive defenseAbstract
The rapid integration of critical infrastructures, organizations, and governmental systems into cyberspace and the Internet of Things (IoT) has significantly expanded the cyberattack surface. IoT ecosystems interconnect resource-constrained devices, sensors, gateways, and cloud platforms, creating cyber-physical environments where security breaches can lead not only to data loss but also to physical and economic damage. The absence of public transparency, anonymity, low entry barriers, and unclear geographic boundaries in cyberspace has fostered cyber warfare, cybercrime, cyber terrorism, and cyber espionage, challenging the effectiveness of traditional national security frameworks. Despite extensive analysis of cyber incidents over the past decade, there is still no universally accepted definition of a cyberattack, resulting in inconsistent legal interpretations and fragmented regulatory responses. At the same time, deep learning (DL) models are increasingly adopted for IoT-based cyber-security solutions such as intrusion detection, anomaly detection, and threat classification. However, conventional performance metrics alone are insufficient to evaluate DL models operating in adversarial environments. These models are vulnerable to data poisoning, evasion attacks, model inversion, and backdoor injections that can severely compromise their reliability.
References
S. Mohamed and S. Aydin, "IoT-based intrusion detection systems: A review," Smart Science, vol. 10, no. 4, pp. 265–282, 2022.
J. Arshad, M. A. Azad, M. M. Abdeltaif, and K. Salah, "An intrusion detection framework for energy constrained IoT devices," Mechanical Systems and Signal Processing, vol. 136, Art. no. 106436, pp. 1–13, 2020.
Y. Jin, Y. Hu, J. Huang, and J. Zhang, "Study on influences of model parameters on the performance of SVM," In Proceedings of the 2011 International Conference on Electrical and Control Engineering (ICECE), 2011.
M. A. Siddiqi and W. Pak, "Tier-based optimization for synthesized network intrusion detection system," IEEE Access, vol. 10, pp. 108530–108544, 2022.
T. Kim and W. Pak, "Early detection of network intrusions using a GAN-based one-class classifier," IEEE Access, vol. 10, pp. 119357–119367, 2022.
K. Dietz, M. Mühlhäuser, J. Kögel, S. Schwinger, M. Sichermann, and M. Seufert, "The missing link in network intrusion detection: Taking AI/ML research efforts to users," IEEE Access, vol. 12, pp. 79815–79837, 2024.
A. M. Ibrahimy, F. Dewanta, and M. E. Aminanto, "Lightweight machine learning prediction algorithm for network attack on software defined network," In Proceedings of the IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob), Bandung, Indonesia, Dec. 2022.
G. Islam, B. Fu, Y. Yang, and Q. Wei, "A multi-distance ensemble and feature clustering based feature selection approach for network intrusion detection," in Proceedings of the International Symposium on Sensing and Instrumentation in 5G and IoT Era (ISSI), Shanghai, China, Nov. 2022.
T.-C. Vuong, H. Tran, M. X. Trang, V.-D. Ngo, and T. V. Luong, "A comparison of feature selection and feature extraction in network intrusion detection systems," In Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Chiang Mai, Thailand, 2022.
R. B. Said, Z. Sabir, and I. Askerzade, "CNN-BiLSTM: A hybrid deep learning approach for network intrusion detection system in software-defined networking with hybrid feature selection," IEEE Access, vol. 11, pp. 138732–138747, 2023.
Y. Kim, J. Kim, and D. Kim, "Hi-MLIC: Hierarchical multilayer lightweight intrusion classification for various intrusion scenarios," IEEE Access, vol. 12, pp. 120098–120115, 2024.
Z. Azam, M. M. Islam, and M. N. Huda, "Comparative analysis of intrusion detection systems and machine learning-based model analysis through decision tree," IEEE Access, vol. 11, pp. 80348–80391, 2023.
S. Pitafi, T. Anwar, I. D. M. Widia, and B. Yimwadsana, "Revolutionizing perimeter intrusion detection: A machine learning-driven approach with curated dataset generation for enhanced security," IEEE Access, vol. 11, pp. 106954–106966, 2023.
T. J. Lucas, I. S. de Figueiredo, C. A. C. Tojeiro, A. M. G. de Almeida, R. Scherer, and J. R. F. Brega, "A comprehensive survey on ensemble learning-based intrusion detection approaches in computer networks," IEEE Access, vol. 11, pp. 122638–122676, 2023.
Z. Wang, Y. Zeng, Y. Liu, and D. Li, "Deep belief network integrating improved kernel-based extreme learning machine for network intrusion detection," IEEE Access, vol. 9, pp. 16062–16091, 2021.
G. Abdelmoumin, D. B. Rawat, and A. Rahman, "On the performance of machine learning models for anomaly-based intelligent intrusion detection systems for the Internet of Things," IEEE Internet of Things Journal, vol. 9, no. 6, pp. 4280–4290, 2022.
S. Otoum, B. Kantarci, and H. T. Mouftah, "On the feasibility of deep learning in sensor network intrusion detection," IEEE Networking Letters, vol. 1, no. 2, pp. 68–71, 2019.
N. Tran, H. Chen, J. Bhuyan, and J. Ding, "Data curation and quality evaluation for machine learning-based cyber intrusion detection," IEEE Access, vol. 10, pp. 121900–121923, 2022.
B. Gao, B. Bu, W. Zhang, and X. Li, "An intrusion detection method based on machine learning and state observer for train-ground communication systems," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 6608–6620, 2022.
B. Bojarajulu and S. Tanwar, "Customized convolutional neural network model for IoT botnet attack detection," Signal, Image and Video Processing, 2024.
B. Bojarajulu, S. Tanwar, and T. P. Singh, "Improved deep maxout for IoT botnet attack detection with LDA based selected feature set," in Proceedings of the 14th International Conference on Computing, Communication and Networking Technologies (ICCCNT), New Delhi, India, Jul. 2023.
A. M. Banaamah and I. Ahmad, "Intrusion detection in IoT using deep learning," Sensors, vol. 22, no. 21, Art. no. 8417, 2022.
E. Altulaihan, M. A. Almaiah, and A. Aljughaiman, "Anomaly detection IDS for detecting DoS attacks in IoT networks based on machine learning algorithms," Sensors, vol. 24, no. 2, Art. no. 713, 2024.
M. A. Alsoufi, S. Razak, M. Md Siraj, I. Nafea, F. A. Ghaleb, F. Saeed, and M. Nasser, "Anomaly-based intrusion detection systems in IoT using deep learning: A systematic literature review," Applied Sciences, vol. 11, no. 18, Art. no. 8383, 2021.
A. A. Alahmadi, M. Aljabri, F. Alhaidari, D. J. Alharthi, G. E. Rayani, L. Alotaibi, and O. B. Bajandouh, "DDoS attack detection in IoT-based networks using machine learning models: A survey and research directions," Electronics, vol. 12, no. 14, Art. no. 3103, 2023.
