Optimization of Intrusion Detection Using Likely Point PSO and Enhanced LSTM-RNN Hybrid Technique in Communication Networks

Donkol, Ahmed; Hafez, Ali G.; Hussein, Aziza I.; Mabrook, M. Mourad

doi:10.1109/access.2023.3240109

Cited by 18 publications

(12 citation statements)

References 37 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Whale Integrated LSTM (WILS) framework for intrusion detection by B. Jothi et al [29], hybrid metaheuristicsdeep learning based IDS by P. Sanju et al [30], Enhanced LSTM (ELSTM) and Recurrent Neural Network (RNN) combination based IDS developed by A. A. E. B. Donkol et al [31] are few of the sophisticated IDS development approaches with promising performance. These complex methods are focused on detection performance and ignore practical applications.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

Racherla,

Sripathi,

Faruqui

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT) represents a swiftly expanding sector that is pivotal in driving the innovation of today's smart services. However, the inherent resource-constrained nature of IoT nodes poses significant challenges in embedding advanced algorithms for cybersecurity, leading to an escalation in cyberattacks against these nodes. Contemporary research in Intrusion Detection Systems (IDS) predominantly focuses on enhancing IDS performance through sophisticated algorithms, often overlooking their practical applicability. This paper introduces Deep-IDS, an innovative and practically deployable Deep Learning (DL)-based IDS. It employs a Long-Short-Term-Memory (LSTM) network comprising 64 LSTM units and is trained on the CIC-IDS2017 dataset. Its streamlined architecture renders Deep-IDS an ideal candidate for edge-server deployment, acting as a guardian between IoT nodes and the Internet against Denial of Service (DoS), Distributed Denial of Service (DDoS), Brute Force (BRF), Man-in-the-Middle (MITM), and Replay (RP) Attacks. A distinctive aspect of this research is the trade-off analysis between the intrusion detection rate and the false alarm rate, facilitating the real-time performance of the Deep-IDS. The system demonstrates an exemplary detection rate of 96.8% and an overall classification accuracy of 97.67%. Furthermore, Deep-IDS achieves precision, recall, and F1-scores of 97.67%, 98.17%, and 97.91%, respectively. On average, Deep-IDS requires 1.49 seconds to identify and mitigate intrusion attempts, effectively blocking malicious traffic sources. The remarkable efficacy, swift response time, innovative design, and novel defense strategy of Deep-IDS not only secure IoT nodes but also their interconnected subnetworks, thereby positioning Deep-IDS as a leading intrusion detection system for IoT-enhanced computer networks.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

Racherla,

Sripathi,

Faruqui

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The model was designed to detect only DOS attacks. A hybrid IDS is created involving ELSTM and RNN approaches [30]. The IDS processes the data reduced using LPPSO method.…”

Section: Related Workmentioning

confidence: 99%

A Novel Hybrid Feature Selection with Cascaded LSTM: Enhancing Security in IoT Networks

Sundaram,

Natarajan,

Perumalsamy

et al. 2024

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The rapid growth of the Internet of Things (IoT) has created a situation where a huge amount of sensitive data is constantly being created and sent through many devices, making data security a top priority. In the complex network of IoT, detecting intrusions becomes a key part of strengthening security. Since IoT environments can be easily affected by a wide range of cyber threats, intrusion detection systems (IDS) are crucial for quickly finding and dealing with potential intrusions as they happen. IDS datasets can have a wide range of features, from just a few to several hundreds or even thousands. Managing such large datasets is a big challenge, requiring a lot of computer power and leading to long processing times. To build an efficient IDS, this article introduces a combined feature selection strategy using recursive feature elimination and information gain. Then, a cascaded long–short-term memory is used to improve attack classifications. This method achieved an accuracy of 98.96% and 99.30% on the NSL-KDD and UNSW-NB15 datasets, respectively, for performing binary classification. This research provides a practical strategy for improving the effectiveness and accuracy of intrusion detection in IoT networks.

show abstract

“…The model was trained using the CICIDS 2017 and CICIDS 2018 datasets and attained an accuracy of 99.99% and 99.10%. Ahmed et al [34] suggested an enhanced IDS using a Likely point PSO (LPPSO) + hybrid LSTM-RNN techniques. The LPPSO algorithm solves the over-fitting problem and optimizes feature selection.…”

Section: Related Workmentioning

confidence: 99%

DL-ADS: Improved Grey Wolf Optimization Enabled AE-LSTM Technique for Efficient Network Anomaly Detection in Internet of Thing Edge Computing

Manokaran,

Vairavel

2024

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT) technology has begun to proliferate in recent years, which simultaneously increases the number of attacks. Owing to the massive volume and multi-dimensional data in IoT, anomaly detection leads to low prediction accuracy and a high false alarm rate. Further, there is a deficit of real-world test datasets for anomaly detection. This work aims to generate a novel real-time anomaly detection dataset and proposes an efficient anomaly detection model using an Improved Grey Wolf Optimization (IGWO)-enabled Long Short-Term Memory (LSTM) network in IoT edge scenarios. Dataset generation is carried out using a testbed setup containing Raspberry Pi 4 and sensors connected by a lightweight Message Queuing Telemetry Transport (MQTT) protocol. An autoencoder is used for feature reduction as it can investigate the input characteristics without sacrificing vital information. The LSTM classifier parameters, such as learning rate, optimizer, and batch size, are tuned precisely using IGWO techniques. The experimental results disclose that the proposed model achieves an accuracy of 99.11% for the testbed dataset, which is better than recent models. To confirm the generalizability of our model, the CICIDS 2017, DS2OS, and MQTTset standard datasets are applied explicitly. The developed model outcomes are statistically verified using the Wilcoxon signed rank test.INDEX TERMS Anomaly detection, autoencoder, improved grey wolf optimization, Internet of Things security, LSTM networks, MQTT, Wilcoxon signed rank test.

show abstract

Optimization of Intrusion Detection Using Likely Point PSO and Enhanced LSTM-RNN Hybrid Technique in Communication Networks

Cited by 18 publications

References 37 publications

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

A Novel Hybrid Feature Selection with Cascaded LSTM: Enhancing Security in IoT Networks

DL-ADS: Improved Grey Wolf Optimization Enabled AE-LSTM Technique for Efficient Network Anomaly Detection in Internet of Thing Edge Computing

Contact Info

Product

Resources

About