Unauthorized users may attack centralized controllers as an attractive target in software-defined networking (SDN)-based industrial cyber-physical systems (CPS). Managing high-complexity deep learning (DL)-based intru...
详细信息
Unauthorized users may attack centralized controllers as an attractive target in software-defined networking (SDN)-based industrial cyber-physical systems (CPS). Managing high-complexity deep learning (DL)-based intrusionclassification to recognize and prevent attacks in the industrial Internet of Things (IIoT) networks with low-latency requirements is challenging. Moreover, a centralized DL-based intrusiondetection system (IDS) leads to privacy concerns and communication overhead issues during data uploading to a cloud server for training processes in IIoT environments. This study proposes federated learning (FL)-based low-complexity intrusion detection and classification in SDN-enabled industrial CPS. This framework utilizes Chi-square and Pearson correlation coefficient (PCC) feature selection methods to select potential features, which help reduce the model's complexity and boost performance. The proposed model evaluated the SDN and IIoT-related InSDN and Edge-IIoTset datasets. The model measurement shows that the proposed model achieves high accuracy, low computational cost, and a low-complexity model architecture compared with state-of-the-art approaches.
The Internet of Things (IoT) has been introduced as a breakthrough technology that integrates intelligence into everyday objects, enabling high levels of connectivity between them. As the IoT networks grow and expand,...
详细信息
ISBN:
(纸本)9783031708183;9783031708190
The Internet of Things (IoT) has been introduced as a breakthrough technology that integrates intelligence into everyday objects, enabling high levels of connectivity between them. As the IoT networks grow and expand, they become more susceptible to cybersecurity attacks. A significant challenge in current intrusiondetection systems for IoT includes handling imbalanced datasets where labeled data are scarce, particularly for new and rare types of cyber attacks. Existing literature often fails to detect such underrepresented attack classes. This paper introduces a novel intrusiondetection approach designed to address these challenges. By integrating Self Supervised Learning (SSL), Few Shot Learning (FSL), and Random Forest (RF), our approach excels in learning from limited and imbalanced data and enhancing detection capabilities. The approach starts with a Deep Infomax model trained to extract key features from the dataset. These features are then fed into a prototypical network to generate discriminate embedding. Subsequently, an RF classifier is employed to detect and classify potential malware, including a range of attacks that are frequently observed in IoT networks. The proposed approach was evaluated through two different datasets, MaleVis and WSN-DS, which demonstrate its superior performance with accuracies of 98.60% and 99.56%, precisions of 98.79% and 99.56%, recalls of 98.60% and 99.56%, and F1-scores of 98.63% and 99.56%, respectively.
The Internet of Things (IoT) has been used in various critical fields, including healthcare, elderly surveillance, autonomous transportation, and energy management. As a result of its emergence, several IoT-based smar...
详细信息
ISBN:
(纸本)9783031162107;9783031162091
The Internet of Things (IoT) has been used in various critical fields, including healthcare, elderly surveillance, autonomous transportation, and energy management. As a result of its emergence, several IoT-based smart applications have been established in various domains. Wireless Sensor Networks (WSNs) are the most common infrastructure for these applications. A WSN is a network that includes many diverse sensor nodes. These nodes are scattered across large areas, collecting data and transmitting it wirelessly. These networks are subjected to a variety of security threats. Protecting WSNs against incoming threats is both necessary and challenging. This paper presents a deep transfer learning based approach for intrusion detection and classification in WSNs. To identify and categorize Denial-of-Service (DoS) attacks, we deployed several pre-trained Convolutional Neural Networks (CNNs). To improve the classification performance, the final outputs of the CNN models are combined using ensemble learning, precisely the majority voting method. We used the recent and rich WSN-DS dataset for the experiments, which includes four types of DoS attacks as well as benign samples. The experimental findings confirm the effectiveness of the suggested method, which provides an accuracy of 100%.
A phishing email is a legitimate-looking email which is designed to fool the recipient into believing that it is a genuine email, and either reveals sensitive information or downloads malicious software through clicki...
详细信息
ISBN:
(纸本)9781509054435
A phishing email is a legitimate-looking email which is designed to fool the recipient into believing that it is a genuine email, and either reveals sensitive information or downloads malicious software through clicking on malicious links contained in the body of the email. Given that phishing emails cost UK consumers 174m pound in 2015, this paper proposal is driven by a problem whose resolution will have a great impact on people's lives in the UK and in the world. In this paper, we proposed a Neural Network (NN)-based model for detections and classifications of phishing emails using publically available email datasets for both benign and phishing emails. The results of the experiments are presented in order to demonstrate the effectiveness of the model in terms of accuracy, true-positive rate, false-positive rate, network performance and error histogram.
暂无评论