Design of an Intrusion Detection Model for IoT-Enabled Smart Home

IEEE Access, Год журнала: 2023, Номер unknown, С. 1 - 1

Опубликована: Янв. 1, 2023

Machine learning (ML) provides effective solutions to develop efficient intrusion detection system (IDS) for various environments. In the present paper, a diversified study of ensemble machine algorithms has been carried out propose design an and time-efficient IDS Internet Things (IoT) enabled environment. this data captured from network traffic real-time sensors IoT-enabled smart environment analyzed classify predict types attacks. The performance Logistic Regression, Random Forest, Extreme Gradient Boosting, Light Boosting classifiers have benchmarked using open-source largely imbalanced dataset 'DS2OS' that consists 'normal' 'anomalous' traffic. An model "LGB-IDS" proposed LGBM library ML after validating its superiority over other techniques on basis majority voting. is suitably validated certain metrics such as train test accuracy, time efficiency, error-rate, true-positive rate (TPR), false-negative (FNR). experimental results reveal XGB almost equal but efficiency much better than RF, classifiers. main objective paper with high reduced false alarm rate. show achieves accuracy 99.92% comes be higher prevalent algorithms-based models. threat greater 90% less 100%. Time complexity also very low compared algorithms.

Язык: Английский

---

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

Sensors, Год журнала: 2024, Номер 24(7), С. 2188 - 2188

Опубликована: Март 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.

Язык: Английский

---

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

IEEE Access, Год журнала: 2024, Номер 12, С. 63584 - 63597

Опубликована: Янв. 1, 2024

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

Язык: Английский

---

IoT Intrusion Detection System Based on Machine Learning

Electronics, Год журнала: 2023, Номер 12(20), С. 4289 - 4289

Опубликована: Окт. 17, 2023

With the rapid development of Internet Things (IoT), number IoT devices is increasing dramatically, making it increasingly important to identify intrusions on these devices. Researchers are using machine learning techniques design effective intrusion detection systems. In this study, we propose a novel system that efficiently detects network anomalous traffic. To reduce feature dimensions data, employ binary grey wolf optimizer (BGWO) heuristic algorithm and recursive elimination (RFE) select most relevant subset for target variable. The synthetic minority oversampling technique (SMOTE) used oversample class mitigate impact data imbalance classification results. preprocessed then classified XGBoost, hyperparameters model optimized Bayesian optimization with tree-structured Parzen estimator (BO-TPE) achieve highest performance. validate effectiveness proposed method, conduct multiclass experiments five commonly datasets. results show our method outperforms state-of-the-art methods in four out It noteworthy achieves perfect accuracy, precision, recall, an F1 score 1.0 BoT-Iot WUSTL-IIOT-2021 datasets, further validating approach.

Язык: Английский

---

SIM-FED: Secure IoT malware detection model with federated learning

Computers & Electrical Engineering, Год журнала: 2024, Номер 116, С. 109139 - 109139

Опубликована: Март 30, 2024

Язык: Английский

---

A Deep Learning-Based Framework for Strengthening Cybersecurity in Internet of Health Things (IoHT) Environments

Applied Sciences, Год журнала: 2024, Номер 14(11), С. 4729 - 4729

Опубликована: Май 30, 2024

The increasing use of IoHT devices in healthcare has brought about revolutionary advancements, but it also exposed some critical vulnerabilities, particularly cybersecurity. is characterized by interconnected medical sharing sensitive patient data, which amplifies the risk cyber threats. Therefore, ensuring data’s integrity, confidentiality, and availability essential. This study proposes a hybrid deep learning-based intrusion detection system that uses an Artificial Neural Network (ANN) with Bidirectional Long Short-Term Memory (BLSTM) Gated Recurrent Unit (GRU) architectures to address cybersecurity threats IoHT. model was tailored meet complex security demands rigorously tested using Electronic Control ECU-IoHT dataset. results are impressive, achieving 100% accuracy, precision, recall, F1-Score binary classifications maintaining exceptional performance multiclass scenarios. These findings demonstrate potential advanced AI methodologies safeguarding environments, providing high-fidelity while minimizing false positives.

Язык: Английский

---

Harnessing Machine Learning Intelligence Against Cyber Threats

Advances in business strategy and competitive advantage book series, Год журнала: 2024, Номер unknown, С. 319 - 352

Опубликована: Авг. 28, 2024

The spread of cyberthreats in the digital age presents serious concerns to national security, stability economy, and personal privacy. Traditional security methods are unable keep up with increasing sophistication size cyberattacks. With facilitating quick identification mitigation cyberthreats, machine learning (ML) has revolutionary potential improve cybersecurity measures. But applying ML this field also brings important moral legal issues, particularly light international cybercrimes. This chapter comprehensively explores learning's dual nature cybersecurity, emphasizing both its advantages disadvantages. It talk about state cyber threats today, how is being incorporated into ramifications using investigations.

Язык: Английский

---

Class imbalance data handling with optimal deep learning-based intrusion detection in IoT environment

Soft Computing, Год журнала: 2024, Номер 28(5), С. 4519 - 4529

Опубликована: Фев. 5, 2024

Язык: Английский

---

Machine learning security and privacy: a review of threats and countermeasures

EURASIP Journal on Information Security, Год журнала: 2024, Номер 2024(1)

Опубликована: Апрель 23, 2024

Abstract Machine learning has become prevalent in transforming diverse aspects of our daily lives through intelligent digital solutions. Advanced disease diagnosis, autonomous vehicular systems, and automated threat detection triage are some prominent use cases. Furthermore, the increasing machine critical national infrastructures such as smart grids, transport, natural resources makes it an attractive target for adversaries. The to systems is aggravated due ability mal-actors reverse engineer publicly available models, gaining insight into algorithms underpinning these models. Focusing on landscape we have conducted in-depth analysis critically examine security privacy threats factors involved developing adversarial attacks. Our highlighted that feature engineering, model architecture, targeted system knowledge crucial formulating one successful attack can lead other attacks; instance, poisoning attacks membership inference backdoor We also reviewed literature concerning methods techniques mitigate whilst identifying their limitations including data sanitization, training, differential privacy. Cleaning sanitizing datasets may challenges, underfitting affecting performance, whereas does not completely preserve model’s Leveraging surfaces mitigation techniques, identify potential research directions improve trustworthiness systems.

Язык: Английский

---

Enhancing Cyberattack Detection Using Dimensionality Reduction With Hybrid Deep Learning on Internet of Things Environment

IEEE Access, Год журнала: 2024, Номер 12, С. 84752 - 84762

Опубликована: Янв. 1, 2024

Язык: Английский

---