Aug 2026· Italian National Conference on Sensors· 0 citations· 58 references
TL;DR
LSTM had good detection for frequent attacks and slow-changing patterns, which shows its capacity in learning long-lasting dependencies, which shows its capacity in learning long-lasting dependencies.
Abstract
Traditional rule-based intrusion detection systems generally fail in identifying unknown or evolving threats; thus, automated and adaptive kinds of methods are crucial. Deep learning models provide promising solutions, but many recent studies depend on hybrid architecture, which increase the computational cost and reduce deploying ability on real-time or resource-limited systems. In this paper, we present and test a standalone LSTM model for multiclass cyberattack detection based on a CIC_IoT_Dataset2023, a recent labeled dataset that mirrors the actual network environment containing 33 attack categories. The dataset was extremely imbalanced as benign traffic accounted for most of the classes. To detect such attacks, we used the Synthetic Minority Oversampling Technique (SMOTE) to increase the frequency of less common types of address. The pre-processed dataset was then employed to train four models (RNN, CNN, DNN and the proposed LSTM) for performance analysis with sequential data. The proposed LSTM model achieved an accuracy between 2% and 7%. LSTM had good detection for frequent attacks and slow-changing patterns, which shows its capacity in learning long-lasting dependencies. The results demonstrate that a simple, lightweight standalone LSTM model can be used for effective and realistic intrusion detection without the need for complex hybrid architecture.
An intelligent cyberattack detection system that applies machine learning and deep learning techniques to classify network traffic as either normal or malicious, and demonstrates the potential of machine learningbased intrusion detection systems in improving network security and supporting the protection of modern smart environments.
KADADHARAPU ANUPRIYA, Dr.S.SWATHI RAO· International Journal of Eng...· 0 citations
Network infrastructure has become more complex and the amount of cybersecurity challenges has grown with the introduction of cloud computing, the Internet of Things (IoT) and next-generation communication technologies. The known attack and known signatures are the reasons why traditional IDSs fail to detect sophisticated and new attacks; they are signature-based and programmed by hand. To overcome these drawbacks, this work presents a deep learning-based cybersecurity framework for proactively detecting the intrusion in CSE-CIC-IDS2018 benchmark dataset. The proposed system combines spatial and temporal features of network traffic using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network architecture with a systematic data preprocessing pipeline. In the preprocessing stage, data quality and learning efficiency are enhanced by data cleaning, handling missing data, removing duplicate data, encoding labels, normalizing features, and splitting the data into training and testing sets. The CNN part is used to automatically learn discriminative spatial features, and the LSTM was used to learn the sequential traffic dependencies to see the relation between the sequential sequence and attack detection capability was improved. Experiments were carried out on Python, TensorFlow, Keras and Google Colab with GPU support. The proposed framework was evaluated according to the accuracy, precision, recall, F1-score, and ROC-AUC and the results were found to be 98.64%, 98.41%, 98.18%, 98.29%, and 99.12%, respectively, which are considered to be excellent classification results and strong discrimination ability. Moreover, the framework demonstrated good computational efficiency with an average inference time of 2.8ms per network flow and a moderate use of GPU memory. Results of comparative analysis with the latest deep learning-based intrusion detection methods also validate the competitiveness and applicability of the proposed framework. The results highlight the efficiency, reliability, and effectiveness of the hybrid CNN-LSTM framework in proactively detecting network intrusions in contemporary cybersecurity settings.
The framework introduces CNN–BiLSTM deep learning networks to represent traffic in a spatiotemporal manner and adopts ensemble machine learning classifiers to enhance the robustness of traffic detection and its interpretability, to enhance the robustness of traffic detection and its interpretability.
Ramesh N. S. V. S. C. Sripada, A. Bhavani, Kiran B. Malagi et al.· Discover Computing· 0 citations
The rapid growth of digital communication technologies, cloud computing, and Internet of Things (IoT) devices has
increased both the frequency and sophistication of cyber-attacks, making effective intrusion detection an essential component of
modern cybersecurity systems. Traditional signature-based intrusion detection systems (IDS) are effective against known attacks
but fail to detect previously unseen or evolving threats. This study investigates the application of deep learning models for binary
network intrusion detection using the NSL-KDD benchmark dataset. Three standalone architectures, Convolutional Neural
Networks (CNN), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNN), are implemented and
evaluated, alongside a CNN-LSTM Hybrid model that integrates spatial and sequential learning, and a DNN-LSTM Ensemble
model that combines independently trained DNN and LSTM predictions through weighted averaging. Following data cleaning,
categorical encoding, normalization, and Random Forest-based feature selection (41 features reduced to 20), all models were
trained and evaluated under identical conditions using Accuracy, Precision, Recall, F1-Score, ROC-AUC, training time, and
inference time. The standalone DNN model achieved the best overall performance, with 80.98% accuracy, 97.08% precision,
68.66% recall, 80.43% F1-score, and 96.11% ROC-AUC, while also requiring the shortest training time (39.69 s). The CNNLSTM Hybrid model attained the highest precision (97.23%) but did not outperform the standalone architectures overall, and
the DNN-LSTM Ensemble produced balanced but not superior results. These findings indicate that carefully designed
standalone architectures can match or exceed the performance of more complex hybrid and ensemble models for binary
intrusion detection, while incurring substantially lower computational cost. The study contributes a controlled, commonframework comparison of five deep learning architectures and provides practical guidance for selecting computationally
efficient models for anomaly-based intrusion detection.
Ketki Naik, Sanjeev Ghosh· International Journal for Re...· 0 citations
A Hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model for effective IoT malware detection is proposed, which enhances detection capability for both known and zero-day attacks.
A two-tier hybrid IDS that uses a Random Forest model for quick initial detection and a Neural Network for deeper analysis of suspicious traffic is proposed that provides a balanced and efficient solution that overcomes key limitations of existing IDS models and offers a pathway towards a more robust real-time IoT intrusion detection.
Research Paper, Wong Zoey, Yu Watanabe et al.· International Journal of Eme...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
