DeepSDN: Deep Learning Based Software Defined Network Model for Cyberthreat Detection in IoT Network DOI

Korsten Hendrikus H.M.,

K. Srinivasa Reddy

ACM Transactions on Internet Technology, Год журнала: 2025, Номер unknown

Опубликована: Май 29, 2025

The Internet of Things (IoT) presents new challenges to traditional communication models, particularly in terms security, which are exacerbated by the rapid evolution cyberthreats. Traditional security methods, especially those using Machine Learning often struggle with limited computational resources available, making it difficult detect attacks across entire network. Software-defined networks (SDN) offer a solution centralizing policies, enabling more effective implementation and enforcement. study investigates SDN architecture from perspective. This paper proposes Deep Learning-based for IoT can significantly enhance real-time cyberthreat detection. Specifically, secure channel is first designed blockchain-based authentication resist well-known intruders. Second, deep learning convergence model an adaptive threshold scoring method that stops all local training allows edge models contribute cloud until specified accuracy achieved. To achieve low CPU usage provide services, next used as cloud-based system administrator protect zero-day sending requests devices controller. efficiency proposed framework demonstrated simulations two different network datasets E-IIoT ToN-IoT against various results compared similar works. effectively detects mitigates cyberthreats such DDoS, Black-Sink-Worm hole, MitM, Ransomware. It achieves high performance 99.15% accuracy, 99.31% precision, 98.97% recall, 99.14% F1 score, on average while less power protection.

Язык: Английский

Hybrid Machine Learning-Based Fault-Tolerant Sensor Data Fusion and Anomaly Detection for Fire Risk Mitigation in IIoT Environment DOI Creative Commons
Jayameena Desikan, Sushil Kumar Singh,

A. Jayanthiladevi

и другие.

Sensors, Год журнала: 2025, Номер 25(7), С. 2146 - 2146

Опубликована: Март 28, 2025

In the oil and gas IIoT environment, fire detection systems heavily depend on sensor data, which can be prone to inaccuracies due faulty or unreliable sensors. These issues, such as noise, missing values, outliers, drift, readings, lead delayed missed predictions, posing significant safety operational risks in industrial IoT environment. This paper presents an approach for handling sensors edge servers within environment enhance reliability accuracy of prediction through multi-sensor fusion preprocessing, machine learning (ML)-driven probabilistic model adjustment, uncertainty handling. First, a real-time anomaly statistical assessment mechanism is employed preprocess filtering out readings normalizing data from multiple types using dynamic thresholding, adapts behavior real-time. The proposed also deploys algorithms dynamically adjust models based reliability, thereby improving even presence data. A belief mass assignment introduced, giving more weight reliable ensure they have stronger influence detection. Simultaneously, update strategy continuously adjusts trust levels, reducing impact over time. Additionally, measurements Hellinger Deng entropy, along with Dempster-Shafer Theory, enable integration conflicting inputs decision-making improves by managing discrepancies provides solution mitigating environments.

Язык: Английский

Процитировано

1
DeepSDN: Deep Learning Based Software Defined Network Model for Cyberthreat Detection in IoT Network DOI

Korsten Hendrikus H.M.,

K. Srinivasa Reddy

ACM Transactions on Internet Technology, Год журнала: 2025, Номер unknown

Опубликована: Май 29, 2025

The Internet of Things (IoT) presents new challenges to traditional communication models, particularly in terms security, which are exacerbated by the rapid evolution cyberthreats. Traditional security methods, especially those using Machine Learning often struggle with limited computational resources available, making it difficult detect attacks across entire network. Software-defined networks (SDN) offer a solution centralizing policies, enabling more effective implementation and enforcement. study investigates SDN architecture from perspective. This paper proposes Deep Learning-based for IoT can significantly enhance real-time cyberthreat detection. Specifically, secure channel is first designed blockchain-based authentication resist well-known intruders. Second, deep learning convergence model an adaptive threshold scoring method that stops all local training allows edge models contribute cloud until specified accuracy achieved. To achieve low CPU usage provide services, next used as cloud-based system administrator protect zero-day sending requests devices controller. efficiency proposed framework demonstrated simulations two different network datasets E-IIoT ToN-IoT against various results compared similar works. effectively detects mitigates cyberthreats such DDoS, Black-Sink-Worm hole, MitM, Ransomware. It achieves high performance 99.15% accuracy, 99.31% precision, 98.97% recall, 99.14% F1 score, on average while less power protection.

Язык: Английский

Процитировано

0