Enhancing IoT network security through deep learning-powered Intrusion Detection System

Bakhsh, Shahid Allah; Khan, Muhammad Almas; Ahmed, Fawad; Alshehri, Mohammed S.; Ali, Hisham; Ahmad, Jawad

doi:10.1016/j.iot.2023.100936

Cited by 28 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primary focus of the work in [29] was to reduce the complexity and classification time, which improved the accuracy when using DL-based techniques in a cybersecurity IDS for IoT networks. The authors proposed three different models using various deep learning techniques.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Navigating the Cyber Threat Landscape: An In-Depth Analysis of Attack Detection within IoT Ecosystems

AboulEla,

Ibrahim,

Shehmir

et al. 2024

View full text Add to dashboard Cite

The Internet of Things (IoT) is seeing significant growth, as the quantity of interconnected devices in communication networks is on the rise. The increased connectivity of devices has heightened their susceptibility to hackers, underscoring the need to safeguard IoT devices. This research investigates cybersecurity in the context of the Internet of Medical Things (IoMT), which encompasses the cybersecurity mechanisms used for various healthcare devices connected to the system. This study seeks to provide a concise overview of several artificial intelligence (AI)-based methodologies and techniques, as well as examining the associated solution approaches used in cybersecurity for healthcare systems. The analyzed methodologies are further categorized into four groups: machine learning (ML) techniques, deep learning (DL) techniques, a combination of ML and DL techniques, Transformer-based techniques, and other state-of-the-art techniques, including graph-based methods and blockchain methods. In addition, this article presents a detailed description of the benchmark datasets that are recommended for use in intrusion detection systems (IDS) for both IoT and IoMT networks. Moreover, a detailed description of the primary evaluation metrics used in the analysis of the discussed models is provided. Ultimately, this study thoroughly examines and analyzes the features and practicality of several cybersecurity models, while also emphasizing recent research directions.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

“…They can be applied to more sophisticated tasks like image processing and natural language processing. The following state-of-the-art works have adopted DL (non-Transformer-based) methods: [20][21][22][25][26][27][28][29]. The following works have combined DL with ML methods: [30][31][32][33][34][35].…”

Section: Other Methodsmentioning

confidence: 99%

Navigating the Cyber Threat Landscape: An In-Depth Analysis of Attack Detection within IoT Ecosystems

AboulEla,

Ibrahim,

Shehmir

et al. 2024

View full text Add to dashboard Cite

show abstract

“…In [ 108 ], cyberattacks on IoT networks were examined, along with the necessity of effective security protocols. This study proposed the use of several DL models, namely Feed Forward Neural Network (FFNN), Long Short Term Memory (LSTM), and Random Neural Network (RandNN) models, that were each trained on the CIC IoT 2022 dataset.…”

Section: Deep Learning—iot Network Anomaly Detectionmentioning

confidence: 99%

Machine Learning and Deep Learning Techniques for Internet of Things Network Anomaly Detection—Current Research Trends

Rafique,

Abdallah,

Musa

et al. 2024

Sensors

View full text Add to dashboard Cite

With its exponential growth, the Internet of Things (IoT) has produced unprecedented levels of connectivity and data. Anomaly detection is a security feature that identifies instances in which system behavior deviates from the expected norm, facilitating the prompt identification and resolution of anomalies. When AI and the IoT are combined, anomaly detection becomes more effective, enhancing the reliability, efficacy, and integrity of IoT systems. AI-based anomaly detection systems are capable of identifying a wide range of threats in IoT environments, including brute force, buffer overflow, injection, replay attacks, DDoS assault, SQL injection, and back-door exploits. Intelligent Intrusion Detection Systems (IDSs) are imperative in IoT devices, which help detect anomalies or intrusions in a network, as the IoT is increasingly employed in several industries but possesses a large attack surface which presents more entry points for attackers. This study reviews the literature on anomaly detection in IoT infrastructure using machine learning and deep learning. This paper discusses the challenges in detecting intrusions and anomalies in IoT systems, highlighting the increasing number of attacks. It reviews recent work on machine learning and deep-learning anomaly detection schemes for IoT networks, summarizing the available literature. From this survey, it is concluded that further development of current systems is needed by using varied datasets, real-time testing, and making the systems scalable.

show abstract

“…An IDS safeguards communication between devices and detects intrusions across different IoT network layers. Numerous IDS solutions have been developed to secure internet communication [17,18,19,20]. These systems actively monitor network activity for malicious behavior and send alerts to system administrators upon detecting attacks.…”

Section: Related Workmentioning

confidence: 99%

Securing the IoT Cyber Environment: Enhancing Intrusion Anomaly Detection With Vision Transformers

Sana,

Nazir,

Yang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Background and Motivation:The ever-expanding Internet of Things (IoT) landscape presents a double-edged sword. While it fosters interconnectedness, the vast amount of data generated by IoT devices creates a larger attack surface for cybercriminals. Intrusions in these environments can have severe consequences. To combat this growing threat, robust intrusion detection systems (IDS) are crucial. The data comprised by this attack is multivariate, highly complex, non-stationary, and nonlinear. To extract the complex patterns from this complex data, we require the most robust, optimized tools. Methods: Machine learning (ML) and deep learning (DL) have emerged as powerful tools for IDSs, offering high accuracy in detecting and preventing security breaches. This research delves into anomaly detection, a technique that identifies deviations from normal system behavior, potentially indicating attacks. Given the complexity of anomaly data, we explore methods to improve detection performance. Proposed Approach: This research investigates the design and evaluation of a novel IDS. We leverage and optimize supervised ML methods like tree-based Support Vector Machines (SVM), ensemble methods, and neural networks (NN) alongside the cutting-edge DL approach of long short-term memory (LSTM) and vision transformers (ViT). We optimized the hyperparameters of these algorithms using a robust Bayesian optimization approach. Results: The implemented ML models achieved impressive training accuracy, with Random Forest and Ensemble Bagged Tree surpassing 99.90% of accuracy, an AUC of 1.00, an F1-score, and a balanced Matthews Correlation Coefficient (MCC) of 99.78%. While the initial deep learning LSTM model yielded an accuracy of 99.97%, the proposed ViT architecture significantly boosted performance with 100% of all metrics, along with a validation accuracy of 78.70% and perfect training accuracy. Conclusion: Our findings demonstrate the potential of the proposed methods for enhanced attack and intrusion detection. This improved detection capability can be instrumental in safeguarding system integrity, identifying fraudulent activity, and optimizing system performance in IoT networks.

show abstract

Enhancing IoT network security through deep learning-powered Intrusion Detection System

Cited by 28 publications

References 37 publications

Navigating the Cyber Threat Landscape: An In-Depth Analysis of Attack Detection within IoT Ecosystems

Navigating the Cyber Threat Landscape: An In-Depth Analysis of Attack Detection within IoT Ecosystems

Machine Learning and Deep Learning Techniques for Internet of Things Network Anomaly Detection—Current Research Trends

Securing the IoT Cyber Environment: Enhancing Intrusion Anomaly Detection With Vision Transformers

Contact Info

Product

Resources

About