Hybrid Intrusion Detection for IoT, 5G/6G, and Cloud Security: Trends, Challenges, and Future Directions.

This article offers a comprehensive assessment of intrusion detection systems (IDS) with an emphasis on Wi-Fi and 5G-specific solutions to detect, contain, and combat new threats in upcoming convergent 5G and Wi-Fi networks. Manufacturers are investigating the intersection of cellular networks and Wi-Fi due of the significant standardized flexibility made about by the introduction of 5G networks. To guaranty that this convergence is achieved, a number of hypotheses have been put forth. These ideas are based on contemporary networking principles, which call for rearranging network components, dividing control and data planes, and deliberately moving resources toward or away from clients. Convergent architectures feature a number of security issues related to the architecture itself, the access norms, including networked models that support these designs, notwithstanding the possible advantages. The amount of data that flows through these networks and the emergence of zero-day infections that utilize the advantage of unknown signatures call for the creation of accurate, quick, and reliable solutions that can identify and stop threats before they spread throughout the network. However, attackers are increasingly using methods to trick IDS models and fabricate input data. Today's techniques are often resource-intensive and manipulable. Future study should focus on employing adversarial machine learning approaches to overcome these limitations. This provides promising avenues for enhancing IDS robustness and performance in combined 5G/Wi-Fi networks.

1.Dunsin, D., Molla, R., & Esfahani, A. (2026). Hybrid Intrusion Detection System for IoT and Cloud Environments. https://doi.org/10.21203/rs.3.rs-10144004/v1 2.Gupta, S., Verma, D. K., Srivastava, S. K., & Joshi, C. (2026). An Explainable Latent-Attention Hybrid Deep Learning Framework for High-Fidelity Intrusion Detection in IoT and Industrial Cyber Systems. IEEE Access. https://doi.org/10.1109/ACCESS.2026.3701636 3. Achbarou, O., Datsi, T., & Bourkoukou, O. (2025). Enhanced Intrusion Detection System Using Feature Selection and Hybrid Learning Models for High Performance and Efficiency in an IOT environment. Journal of Engineering Research. https://doi.org/10.1016/j.jer.2025.10.016 4. Hakami, H., Faheem, M., & Ahmad, M. B. (2025). Machine learning techniques for enhanced intrusion detection in IoT security. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3542227 5. Sharma, V. (2026). A Literature Review For GPT-6 Astra. 6.Anand, N., & Kumar, M. (2013, July). Modeling and optimization of extraction-transformation-loading (ETL) processes in data warehouse: An overview. In 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT) (pp. 1-5). IEEE. https://doi.org/10.1109/ICCCNT.2013.6726592 7. Anand, N., & Sharma, P. (2014). Data Warehouse Security through Conceptual Models. 8. Anand, P. S. N. (2014). Framework for The Integrated And Validated Model of Data Warehouse. American Journal of Engineering Research (AJER), e-ISSN, 2320-0847. 9. Agarwal, S., Singh, A. P., & Anand, N. (2013, July). Evaluation performance study of Firefly algorithm, particle swarm optimization and artificial bee colony algorithm for non-linear mathematical optimization functions. In 2013 fourth international conference on computing, communications and networking technologies (ICCCNT) (pp. 1-8). IEEE. https://doi.org/10.1109/ICCCNT.2013.6726474 10. Anand, N., Singh, K.J. (2024). A Comprehensive Study of DDoS Attack on Internet of Things Network. In: Swain, B.P., Dixit, U.S. (eds) Recent Advances in Electrical and Electronic Engineering. ICSTE 2023. Lecture Notes in Electrical Engineering, vol 1071. Springer, Singapore. https://doi.org/10.1007/978-981-99-4713-3_56