Deep Learning-Based Intrusion Detection System for Cloud Infrastructure Security

N. Moorthy

doi:10.53941/aiet.2026.100004

Abstract

Cloud infrastructure security has become a main issue that needs to be addressed since organizations are moving their sensitive operations to the cloud and thus are exposing their systems to different kinds of cyber threats like DDoS attacks, brute-force attempts, port scans and insider misuse. Traditional rule-based intrusion detection systems do not adapt to changing attack patterns most of the times; thus, advanced solutions should be developed. One of the key contributions of this research work is a Deep Learning-Based Intrusion Detection System (DL-IDS) utilizing UNSW-NB15 dataset which is designed for providing realistic traffic patterns including both normal and malicious activities. First step in the methodology comprises of applying preprocessing techniques such as one-hot encoding, normalization and feature selection, then followed by feature extraction through an autoencoder which helps in dimensionality reduction and noise elimination. Next, fully connected deep neural network (DNN) is used used for classification, optimized with Adam algorithm also early stopping to secure strong training. The experimental performance shows fantastic results measured in several metrics with 99.12% accuracy, 98.87% precision, 99.54% recall and 99.21% F1-score. Such outcomes point out the model’s ability to operate in middle with respect to sensitivity and specificity which is quite significant to detective reliably the malicious traffic and at same time keep the false alarms very low. High recall figure means that it is very effective in reporting true positives while the precision figure is the corroborating factor of the low rate of clerical mistakes made on the benign traffic. The F1-score is yet another proof of the system’s balanced performance, thus, it can be deployed in real-time in cloud environments. In sum, the DL-IDS framework proposed offers a dynamic, scalable, and effective intrusion detection method which overcomes the drawbacks of traditional systems and presents a significant improvement in the area of cloud infrastructure security.

References

1.
Karkazis, P.A.; Railis, K.; Prekas, S.; et al. Intelligent Network Service Optimization in the Context of 5G/NFV. Signals 2022, 3, 587–610.
2.
Li, Y.; Hu, H.; Liu, W.; et al. An Optimal Active Defensive Security Framework for the Container-Based Cloud with Deep Reinforcement Learning. Electronics 2023, 12, 1598.
3.
Wang, Y.; Dong, S.; Fan, W. Task Scheduling Mechanism Based on Reinforcement Learning in Cloud Computing. Mathematics 2023, 11, 3364.
4.
Gautam, M. Deep Reinforcement Learning for Resilient Power and Energy Systems: Progress, Prospects, and Future Avenues. Electricity 2023, 4, 336–380.
5.
Isong, B.; Kgote, O.; Abu-Mahfouz, A. Insights into Modern Intrusion Detection Strategies for Internet of Things Ecosystems. Electronics 2024, 13, 2370.
6.
Alqahtani, F.; Almutairi, M.; Sheldon, F.T. Cloud Security Using Fine-Grained Efficient Information Flow Tracking. Future Internet 2024, 16, 110.
7.
Uszko, K.; Kasprzyk, M.; Natkaniec, M.; et al. Rule-Based System with Machine Learning Support for Detecting Anomalies in 5G WLANs. Electronics 2023, 12, 2355.
8.
Chauhan, M.; Shiaeles, S. An Analysis of Cloud Security Frameworks, Problems and Proposed Solutions. Network 2023, 3, 422–450.
9.
Aziz, Z.; Bestak, R. Insight into Anomaly Detection and Prediction and Mobile Network Security Enhancement Leveraging K-Means Clustering on Call Detail Records. Sensors 2024, 24, 1716.
10.
Beshah, Y.K.; Abebe, S.L.; Melaku, H.M. Drift Adaptive Online DDoS Attack Detection Framework for IoT System. Electronics 2024, 13, 1004.
11.
Gollapalli, V.S.T.; Srinivasan, K.; Chauhan, G.S.; et al. Cybersecurity Attack Detection Using LSTM and ResNet-50 Hybrid Model with Cloud Deployment. Indo-Am. J. Mech. Eng. 2023, 12, 33–46.
12.
Hernández, D.; Cecilia, J.M.; Cano, J.C.; et al. Flood Detection Using Real-Time Image Segmentation from Unmanned Aerial Vehicles on Edge-Computing Platform. Remote Sens. 2022, 14, 223.
13.
Rashid, K.; Saeed, Y.; Ali, A.; et al. An Adaptive Real-Time Malicious Node Detection Framework Using Machine Learning in Vehicular Ad-Hoc Networks (VANETs). Sensors 2023, 23, 2594.
14.
Yallamelli, A.R.G.; Mamidala, V.; Devarajan, M.V.; et al. Dynamic mathematical hybridized modeling algorithm for e-commerce for order patching issue in the warehouse. Serv. Oriented Comput. Appl. 2024, 1–12. https://doi.org/10.1007/s11761-024-00431-w
15.
Villegas-Ch, W.; Jaramillo-Alcázar, A.; Luján-Mora, S. Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW. Big Data Cogn. Comput. 2024, 8, 8.
16.
Dawood, M.; Tu, S.; Xiao, C.; et al. Cyberattacks and Security of Cloud Computing: A Complete Guideline. Symmetry 2023, 15, 1981.
17.
Sitaraman, S.R.; Khalid, H.M. Robotics automation and adaptive motion planning: A hybrid approach using AutoNav, LIDAR-based SLAM, and DenseNet with Leaky ReLU. J. Trends Comput. Sci. Smart Technol. 2024, 6, 404–423.
18.
Awajan, A. A Novel Deep Learning-Based Intrusion Detection System for IoT Networks. Computers 2023, 12, 34.
19.
Umer, M.; et al. Deep Learning-Based Intrusion Detection Methods in Cyber-Physical Systems: Challenges and Future Trends. Electronics 2022, 11, 3326.
20.
Basani, D.K.R.; Grandhi, S.H.; Abbas, Q. Centralized infrastructure-aware reliable data transaction model in IoT-enabled MANET and cloud using GWO and attention mechanism with LSTM. Int. J. Adv. Res. Inf. Technol. Manag. 2024, 1, 110–134.
21.
Qazi, E.U.H.; Faheem, M.H.; Zia, T. HDLNIDS: Hybrid Deep-Learning-Based Network Intrusion Detection System. Appl. Sci. 2023, 13, 4921.
22.
Alzubi, O.A.; Alzubi, J.A.; Alazab, M.; et al. Optimized Machine Learning-Based Intrusion Detection System for Fog and Edge Computing Environment. Electronics 2022, 11, 3007.
23.
Kavitha, C.; S. M.; Gadekallu, T.R.; et al. Filter-Based Ensemble Feature Selection and Deep Learning Model for Intrusion Detection in Cloud Computing. Electronics 2023, 12, 556.
24.
R M, B.; M K, J.K. Intrusion Detection on AWS Cloud through Hybrid Deep Learning Algorithm. Electronics 2023, 12, 1423.
25.
Parthasarathy, K. Enhanced case-based reasoning with hybrid clustering and evolutionary algorithms for multi-class workload forecasting in autonomic database systems. Int. J. HRM Organ. Behav. 2023, 11, 38–54.
26.
Ramachandran, D.; Albathan, M.; Hussain, A.; et al. Enhancing Cloud-Based Security: A Novel Approach for Efficient Cyber-Threat Detection Using GSCSO-IHNN Model. Systems 2023, 11, 518.
27.
Javed, A.; Ehtsham, A.; Jawad, M.; et al. Implementation of Lightweight Machine Learning-Based Intrusion Detection System on IoT Devices of Smart Homes. Future Internet 2024, 16, 200.
28.
Alduailij, M.; Khan, Q.W.; Tahir, M.; et al. Machine-Learning-Based DDoS Attack Detection Using Mutual Information and Random Forest Feature Importance Method. Symmetry 2022, 14, 1095.
29.
ElKashlan, M.; Elsayed, M.S.; Jurcut, A.D.; et al. A Machine Learning-Based Intrusion Detection System for IoT Electric Vehicle Charging Stations (EVCSs). Electronics 2023, 12, 1044.
30.
Rangelov, D.; et al. Towards an Integrated Methodology and Toolchain for Machine Learning-Based Intrusion Detection in Urban IoT Networks and Platforms. Future Internet 2023, 15, 98.
31.
Induru, V.; Arulkumaran, G. Adaptive cybersecurity monitoring via semantic stream processing and GNN-based trust scoring on IPv4 logs. Int. J. Bus. Manag. Econ. Rev. 2021, 4, 430–443.
32.
Deshmukh, A.; Ravulakollu, K. An Efficient CNN-Based Intrusion Detection System for IoT: Use Case Towards Cybersecurity. Technologies 2024, 12, 203.
33.
Zhong, W.; Yu, N.; Ai, C. Applying big data based deep learning system to intrusion detection. Big Data Min. Anal. 2020, 3, 181–195.
34.
Valivarthi, D.T.; Peddi, S.; Narla, S.; et al. Security-aware side-channel detection through convolutional transformer networks and hybrid LSTM-spectral analysis. Int. J. Adv. Res. Inf. Technol. Manag. Sci. 2024, 1, 17–24.
35.
Adel, A.; Jan, T. Watch the Skies: A Study on Drone Attack Vectors, Forensic Approaches, and Persisting Security Challenges. Future Internet 2024, 16, 250.
36.
El-Gayar, M.M.; Alrslani, F.A.F.; El-Sappagh, S. Smart Collaborative Intrusion Detection System for Securing Vehicular Networks Using Ensemble Machine Learning Model. Information 2024, 15, 583.
37.
Nippatla, R.; Vasamsetty, C.; Kadiyala, B.; et al. Next-generation healthcare frameworks: Lightweight CNNs, capsule networks, and blockchain alternatives for real-time pandemic detection and data security. J. Ubiquitous Comput. Commun. Technol. 2024, 6, 407–428.
38.
Vasani, V.; Bairwa, A.K.; Joshi, S.; et al. Comprehensive Analysis of Advanced Techniques and Vital Tools for Detecting Malware Intrusion. Electronics 2023, 12, 4299.
39.
Srinivasan, K.; Chauhan, G.S.; Jadon, R.; et al. A Real-Time AI-Driven Surgical Monitoring Platform Using Robotics, 3D Convolutional Neural Networks (3D-CNNs), and Bayesian Optimization for Enhanced Precision. In Proceedings of the 2024 International Conference on Computing and Intelligent Reality Technologies (ICCIRT), Coimbatore, India, 5–6 December 2024; pp. 1–6.
40.
Awad, M.; Fraihat, S. Recursive Feature Elimination with Cross-Validation with Decision Tree: Feature Selection Method for Machine Learning-Based Intrusion Detection Systems. J. Sens. Actuator Netw. 2023, 12, 67.
41.
Aldallal, A. Toward Efficient Intrusion Detection System Using Hybrid Deep Learning Approach. Symmetry 2022, 14, 1916.
42.
Dyavani, N.R.; Ubagaram, C.; Garikipati, V.; et al. Adaptive access control in SHACS: Leveraging Markov models and topological data analysis for enhanced cloud security. Int. J. Innov. Technol. Creat. Eng. 2024, 12, 205–225.
43.
Meliboev, A.; Alikhanov, J.; Kim, W. Performance Evaluation of Deep Learning Based Network Intrusion Detection System across Multiple Balanced and Imbalanced Datasets. Electronics 2022, 11, 515.
44.
Shanmugam, V.; Razavi-Far, R.; Hallaji, E. Addressing Class Imbalance in Intrusion Detection: A Comprehensive Evaluation of Machine Learning Approaches. Electronics 2024, 14, 69.
45.
Ramar, V.A.; Kushala, K.; Induru, V.; et al. AI-Augmented Test Automation: Integrating Page Object Model and Behavior-Driven Development for Intelligent and Scalable Software Testing. Int. J. Multidiscip. Res. Growth Eval. 2020, 5, 1078–1085.
46.
Ahmad, I.; Basheri, M.; Iqbal, M.J.; et al. Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection. IEEE Access 2018, 6, 33789–33795.
47.
Alrayes, F.S.; Zakariah, M.; Alzaylaee, M.K.; et al. Optimizing Intrusion Detection System (IDS) with Hybrid Random Forest and CNN-LSTM Models for Improved Accuracy and Efficiency. 2025. Available online: https://www.researchsquare.com/article/rs-6766340/v1 (accessed on).
48.
Adewole, K.S.; Jacobsson, A.; Davidsson, P. Intrusion detection framework for Internet of Things with rule induction for model explanation. Sensors 2025, 25, 1845. https://doi.org/10.3390/s25061845.
49.
Buczak, A.L.; Guven, E. A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Commun. Surv. Tutor. 2015, 18, 1153–1176.
50.
Ali, M.L.; Thakur, K.; Schmeelk, S.; et al. Deep learning vs. machine learning for intrusion detection in computer networks: A comparative study. Appl. Sci. 2025, 15, 1903.
51.
Fan, Z.; You, Z. Research on network intrusion detection based on XGBoost algorithm and multiple machine learning algorithms. Theor. Nat. Sci. 2024, 31, 161–166.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us