Explainable artificial intelligence for intrusion detection in IoT networks: A deep learning based approach

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 238, P. 121751 - 121751

Published: Sept. 25, 2023

Language: Английский

---

A voting gray wolf optimizer-based ensemble learning models for intrusion detection in the Internet of Things

International Journal of Information Security, Journal Year: 2024, Volume and Issue: 23(3), P. 1557 - 1581

Published: Jan. 9, 2024

Abstract The Internet of Things (IoT) has garnered considerable attention from academic and industrial circles as a pivotal technology in recent years. escalation security risks is observed to be associated with the growing interest IoT applications. Intrusion detection systems (IDS) have been devised viable instruments for identifying averting malicious actions this context. Several techniques described papers are thought very accurate, but they cannot used real world because datasets build test models do not accurately reflect simulate network. Existing methods, on other hand, deal these issues, good enough commercial use their lack precision, low rate, receiver operating characteristic (ROC), false acceptance rate (FAR). effectiveness solutions predominantly dependent individual learners consequently influenced by inherent limitations each learning algorithm. This study introduces new approach detecting intrusion attacks an network, which involves ensemble technique based gray wolf optimizer (GWO). novelty lies proposed voting (GWO) model, incorporates two crucial components: traffic analyzer classification phase engine. model employs combine probability averages base learners. Secondly, combination feature selection extraction reduce dimensionality. Thirdly, utilization GWO employed optimize parameters models. Similarly, most authentic that accessible amalgamates multiple generate hybridization information gain (IG) principal component analysis (PCA) was utilized novel incorporated decision tree, random forest, K-nearest neighbor, multilayer perceptron classification. To evaluate efficacy datasets, namely, BoT-IoT UNSW-NB15, were scrutinized. GWO-optimized demonstrates superior accuracy when compared machine learning-based deep Specifically, achieves 99.98%, DR 99.97%, precision 99.94%, ROC 99.99%, FAR 1.30 dataset. According experimental results, optimized achieved 100%, 99.9%, 99.59%, 99.40%, 1.5 tested UNSW-NB15

Language: Английский

---

A Survey of Deep Learning Technologies for Intrusion Detection in Internet of Things

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 4745 - 4761

Published: Jan. 1, 2024

Internet of Things (IoT) is transforming how we live and work its applications are widespread, spanning smart homes, industrial monitoring, cities, healthcare, agriculture, retail Considering wide range applications, it vital to address the security challenges arising from massive collection transmission user data by IoT devices. Intrusion detection systems (IDS) based on deep learning techniques offer new means research directions for resolving issues. Deep models can process large volumes extract complex patterns, making them generally more effective than traditional rule IDSs. While gradually gaining popularity in IDS current lacks a comprehensive summary learning-based context IoT. This paper provides an introduction intrusion technologies, followed detailed comparison, analysis, discussion models, datasets, feature extraction classifiers, preprocessing techniques, experimental design models. It also highlights issues associated with relevant IDS. Finally, concludes providing recommendations assist researchers this domain.

Language: Английский

---

Next–Generation Intrusion Detection for IoT EVCS: Integrating CNN, LSTM, and GRU Models

Mathematics, Journal Year: 2024, Volume and Issue: 12(4), P. 571 - 571

Published: Feb. 14, 2024

In the evolving landscape of Internet Things (IoT) and Industrial IoT (IIoT) security, novel efficient intrusion detection systems (IDSs) are paramount. this article, we present a groundbreaking approach to for IoT-based electric vehicle charging stations (EVCS), integrating robust capabilities convolutional neural network (CNN), long short-term memory (LSTM), gated recurrent unit (GRU) models. The proposed framework leverages comprehensive real-world cybersecurity dataset, specifically tailored IIoT applications, address intricate challenges faced by EVCS. We conducted extensive testing in both binary multiclass scenarios. results remarkable, demonstrating perfect 100% accuracy classification, an impressive 97.44% six-class 96.90% fifteen-class setting new benchmarks field. These achievements underscore efficacy CNN-LSTM-GRU ensemble architecture creating resilient adaptive IDS infrastructures. algorithm, accessible via GitHub, represents significant stride fortifying EVCS against diverse array threats.

Language: Английский

---

DeepLG SecNet: utilizing deep LSTM and GRU with secure network for enhanced intrusion detection in IoT environments

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(4), P. 5459 - 5471

Published: Jan. 30, 2024

Language: Английский

---

Enhanced Intrusion Detection with LSTM-Based Model, Feature Selection, and SMOTE for Imbalanced Data

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(2), P. 479 - 479

Published: Jan. 5, 2024

This study introduces a sophisticated intrusion detection system (IDS) that has been specifically developed for internet of things (IoT) networks. By utilizing the capabilities long short-term memory (LSTM), deep learning model renowned its proficiency in modeling sequential data, our effectively discerns between regular network traffic and potential malicious attacks. In order to tackle issue imbalanced which is prevalent concern development systems (IDSs), we have integrated synthetic minority over-sampling technique (SMOTE) into approach. incorporation allows accurately identify infrequent incursion patterns. The rebalancing dataset accomplished by SMOTE through generation samples belonging class. Various strategies, such as utilization generative adversarial networks (GANs), put forth data imbalance. However, (synthetic technique) presents some distinct advantages when applied detection. characterized simplicity proven efficacy across diverse areas, including implementation this approach straightforward does not necessitate intricate training techniques (GANs). interpretability lies ability generate are aligned with properties original rendering it well suited security applications prioritize transparency. widely embraced field research, demonstrating effectiveness augmenting capacities (IDSs) reducing consequences class conducted thorough assessment three commonly utilized public datasets, namely, CICIDS2017, NSL-KDD, UNSW-NB15. findings indicate LSTM-based (IDS), conjunction address imbalance, outperforms existing methodologies detecting intrusions. provide significant contributions domain security, presenting proactive adaptable safeguarding against advanced cyberattacks. Through mitigation imbalance using SMOTE, AI-driven enhances networks, hence facilitating wider IoT technologies many industries.

Language: Английский

---

A Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes

Sensors, Journal Year: 2024, Volume and Issue: 24(7), P. 2188 - 2188

Published: March 29, 2024

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to and enjoying facilities smart services. IoT marketing experiencing an impressive 16.7% growth rate a nearly USD 300.3 billion market. These eye-catching figures have made it attractive playground for cybercriminals. devices are built using resource-constrained architecture offer compact sizes competitive prices. As result, integrating sophisticated cybersecurity features beyond scope computational capabilities IoT. All these contributed surge in intrusion. This paper presents LSTM-based Intrusion Detection System (IDS) with Dynamic Access Control (DAC) algorithm not only detects but also defends against novel approach achieved 97.16% validation accuracy. Unlike most IDSs, model proposed IDS been selected optimized through mathematical analysis. Additionally, boasts ability identify wider range threats (14 be exact) compared other solutions, translating enhanced security. Furthermore, fine-tuned strike balance between accurately flagging minimizing false alarms. Its performance metrics (precision, recall, F1 score all hovering around 97%) showcase potential this innovative elevate detection rate, exceeding 98%. high accuracy instills confidence its reliability. lightning-fast response time, averaging under 1.2 s, positions among fastest intrusion systems available.

Language: Английский

---

Systematic literature review on intrusion detection systems: Research trends, algorithms, methods, datasets, and limitations

Journal of Intelligent Systems, Journal Year: 2024, Volume and Issue: 33(1)

Published: Jan. 1, 2024

Abstract Machine learning (ML) and deep (DL) techniques have demonstrated significant potential in the development of effective intrusion detection systems. This study presents a systematic review utilization ML, DL, optimization algorithms, datasets research from 2018 to 2023. We devised comprehensive search strategy identify relevant studies scientific databases. After screening 393 papers meeting inclusion criteria, we extracted analyzed key information using bibliometric analysis techniques. The findings reveal increasing publication trends this domain frequently used with convolutional neural networks, support vector machines, decision trees, genetic algorithms emerging as top methods. also discusses challenges limitations current techniques, providing structured synthesis state-of-the-art guide future research.

Language: Английский

---

A hybridization of growth optimizer and improved arithmetic optimization algorithm and its application to discrete structural optimization

Computers & Structures, Journal Year: 2024, Volume and Issue: 303, P. 107496 - 107496

Published: Aug. 1, 2024

Language: Английский

---

RRIoT: Recurrent reinforcement learning for cyber threat detection on IoT devices

Computers & Security, Journal Year: 2024, Volume and Issue: 140, P. 103786 - 103786

Published: Feb. 28, 2024

Language: Английский

---