International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | DDoS Detection Using Deep Learning: A Novel Approach with LSTM and CNN |
|---|---|
| ABSTRACT | The increasing reliance on digital infrastructure has led to a rise in cyber threats, making cybersecurity a critical area of research. Among various cyber threats, Distributed Denial-of-Service (DDoS) attacks are particularly disruptive, targeting network resources and overwhelming them with malicious traffic. Traditional intrusion detection systems (IDS), such as rule-based firewalls and signature-based approaches, struggle to keep up with evolving attack strategies due to their reliance on predefined patterns. As cybercriminals continuously modify their tactics, these traditional methods become less effective in detecting and mitigating advanced threats. To address these challenges, this study proposes a deep learning-based cybersecurity threat detection model utilizing Long Short-Term Memory (LSTM) networks. LSTM is a type of recurrent neural network (RNN) designed to learn from sequential data, making it highly effective in analysing network traffic patterns and identifying anomalies indicative of cyberattacks. The proposed model is trained on the CICIDS2019 dataset, a widely used benchmark dataset for intrusion detection, which contains a diverse range of attack types, including DDoS, botnets, and port scans. The experimental results demonstrate that the LSTM-based model significantly outperforms traditional machine learning approaches, such as K-Nearest Neighbours (KNN) and Artificial Neural Networks (ANN), in terms of accuracy, precision, recall, and F1-score. The LSTM model effectively detects cyber threats with a 98.1% accuracy rate, highlighting its potential for real-world deployment in network security systems. Furthermore, hyperparameter tuning and data pre-processing techniques, such as feature normalization and sequence padding, contribute to the model’s improved performance. This research contributes to the field of AI-driven cybersecurity by showcasing the benefits of deep learning for network intrusion detection. The findings indicate that LSTM-based models can enhance cybersecurity defences by providing real-time, automated threat detection with minimal false positives and false negatives. However, challenges such as computational complexity and real-time adaptability remain areas for further improvement. Future research will focus on enhancing model efficiency, integrating hybrid deep learning architectures (e.g., CNN-LSTM), and improving real-time detection capabilities. Additionally, exploring online learning techniques to enable adaptive threat detection and deploying lightweight models for edge computing will be critical for advancing deep learning-based cybersecurity solutions. |
| TITLE | |
| AUTHOR | KUMWENDA JOHN, SUN LE School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406001 |
| pdf/1_DDoS Detection Using Deep Learning A Novel Approach with LSTM and CNN.pdf | |
| KEYWORDS | |
| References | [1] I. Priyadarshini, P. Mohanty, A. Alkhayyat, R. Sharma, and S. Kumar, “SDN and Application Layer DDoS Attacks Detection in IoT Devices by Attention-Based Bi-LSTM-CNN,” Transactions on Emerging Telecommunications Technologies, vol. 34, no. 8, e4758, 2023. doi: 10.1002/ett.4758. [2] X. Yin, W. Fang, Z. Liu, and D. Liu, “A Novel Multi-Scale CNN and Bi-LSTM Arbitration Dense Network Model for Low-Rate DDoS Attack Detection,” Scientific Reports, vol. 14, no. 1, pp. 1–18, 2024. doi: 10.1038/s41598-024-55814-y. [3] M. S. Elsayed, N.-A. Le-Khac, S. Dev, and A. D. Jurcut, “DDoSNet: A Deep-Learning Model for Detecting Network Attacks,” IEEE Access, vol. 8, pp. 24753–24765, 2022. doi: 10.1109/ACCESS.2020.2971200. [4] V. Gaur and R. Kumar, “DDoSLSTM: Detection of Distributed Denial of Service Attacks on IoT Devices using LSTM Model,” in 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022, pp. 1–6. doi: 10.1109/IC3IoT53935.2022.9767889. [5] K. Saurabh, T. Kumar, U. Singh, O. P. Vyas, and R. Khondoker, “NFDLM: A Lightweight Network Flow Based Deep Learning Model for DDoS Attack Detection in IoT Domains,” arXiv preprint arXiv:2207.10803, 2022. [6] Y. Wei, J. Jang-Jaccard, F. Sabrina, W. Xu, and S. Camtepe, “Reconstruction-Based LSTM-Autoencoder for Anomaly-Based DDoS Attack Detection over Multivariate Time-Series Data,” arXiv preprint arXiv:2305.09475, 2023. [7] Y. Zhang and H. Wang, “Deep Learning Approaches for Encrypted Network Traffic Classification,” Computers & Security, vol. 114, 102589, 2022. doi: 10.1016/j.cose.2021.102589. [8] A. Al-Hasani, I. Abdelmaksoud, and A. Rezk, “A Novel Hybrid CNN-LSTM Framework for Robust DDoS Attack Detection and Classification,” Journal of Cybersecurity & Information Management, vol. 17, no. 1, pp. 21–34, 2026. doi: 10.54216/JCIM.170103. [9] D. Irankunda, K. El Fazazy, T. Hamid, and J. Riffi, “A Hybrid CNN-LSTM Framework Driven by XGBoost for Real-Time DDoS Detection in Industrial IoT,” Discover Internet of Things, Springer, 2026. doi: 10.1007/s43926-026-00366-y. [10] N. Alyassiri, M. Altufaili, and F. Nama, “Hybrid CNN–LSTM Framework for DDoS Detection in 5G-Enabled IoT Environments,” Wasit Journal for Pure Sciences, vol. 4, no. 2, pp. 45–59, 2026. doi: 10.31185/wjps.907. [11] A. Bensaoud and J. Kalita, “CNN-LSTM and Transfer Learning Models for Malware Classification Based on Opcodes and API Calls,” arXiv preprint arXiv:2405.02548, 2024. [12] V. Ramanathan, K. Mahadevan, and S. Dua, “A Novel Supervised Deep Learning Solution to Detect Distributed Denial of Service (DDoS) Attacks on Edge Systems using Convolutional Neural Networks (CNN),” arXiv preprint arXiv:2309.05646, 2023. [13] J. Lee and S. Kim, “Sequential Anomaly Detection Using LSTM Networks for Cybersecurity Applications,” IEEE Access, vol. 11, pp. 33421–33435, 2023. doi: 10.1109/ACCESS.2023.3267845. [14] O. Ebrahem, S. Dowaji, and S. Alhammoud, “A Lightweight Machine Learning Approach for DDoS Detection and Classification,” Scientific Reports, vol. 16, 2026. doi: 10.1038/s41598-026-48535-x. |
