Intrusion Detection Scheme With Dimensionality Reduction in Next Generation Networks

Sood, Keshav; Nosouhi, Mohammad Reza; Nguyen, Dinh Duc Nha; Jiang, Frank; Chowdhury, Morshed; Doss, Robin

doi:10.1109/tifs.2022.3233777

Cited by 28 publications

(17 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, this work can be applied as a decision support system for future IDS. Indeed, the obtained F1-score results do not highly differ from recent works related to DoS in the context of 5G networks, typically ranging from 90% to 98% [27], [28]. Moreover, a mixed approach can be devised, where the NN identifies threats and a human intervention is needed to confirm the blacklisting of that specific UE.…”

Section: Discussionmentioning

confidence: 67%

Real-Time Clustering Based on Deep Embeddings for Threat Detection in 6G Networks

Paolini,

Valcarenghi,

Maggiani

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Trials and deployments of sixth Generation (6G) wireless networks, delivering extreme capacity, reliability, and efficiency, are expected as early as 2030. Attempts from both industry and academia are trying to define the next generation network infrastructure. 6G will set in motion the fourth industrial revolution, delivering global, integrated intelligence. In this scenario, Artificial Intelligence (AI)-assisted architecture for 6G networks will realize knowledge discovery, automatic network adjustment and intelligent service provisioning. The long-term vision for implementing 6G security is to implement an autonomous, self-learning AI-assisted architecture that can perform threat mitigation without disrupting the normal use, enabling the resilience and reliability of the network and fulfilling security automation. This work proposes a first implementation of a proactive threat discovery service to be deployed at 6G base stations, paving the way for collective network intelligence in the context of cybersecurity mechanisms. Specifically, a fully unsupervised Deep Learning (DL) model is presented, able to recognize both Denial of Service (DoS) Hulk and DoS Goldeneye, with 97.0% and 92.2% mean F1-score respectively.

show abstract

Section: Discussionmentioning

confidence: 67%

Real-Time Clustering Based on Deep Embeddings for Threat Detection in 6G Networks

Paolini,

Valcarenghi,

Maggiani

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The security vulnerabilities of smart networks in telecommunication, which are embedded in vehicles, become larger in the management of security protocols and updates. This complex issue is addressed by a comprehensive approach that encapsulates high-end encryption, discreet communication protocols, and continuous observation for a possible danger [24].…”

Section: Literature Reviewmentioning

confidence: 99%

Next-Generation Protection: Leveraging Federated Learning and Blockchain for Intrusion Detection in Smart Vehicle Network

Javaid Ahmad Malik

2024

pst

View full text Add to dashboard Cite

Smart Car's era ushers in new challenges, some of which are in the field of information security such as wise cyber-attack prevention. Traditional IDS systems would lose everything in such a dynamic environment with their centralized architectures, and this approach could create single points of failure and privacy issues. Along with interconnectedness, cyber security becomes an inevitable problem as smart vehicles are incorporated into a daily life. Traditional security mechanisms usually lack scalability and privacy, which brings about the need to develop alter-nate or innovative methods. This research demonstrates a mixed security system that combines both federated learning and blockchain technologies to improve intrusion detection in smart vehicular networks. We evaluated the effectiveness of this framework using four machine learn-ing models as respectively; Support Vector Machine (SVM), Decision Tree, Neural Network, and Random Forest. Empirical results show that SVM had the highest accuracy of both 93.88% in training and 91.84% in validation, which is higher than Decision Tree, Neural Network, and Random Forest models. These findings evidently demonstrate that the federated learning and blockchain are a strong solution for the plausible security of smart vehicle networks; with SVM being employed mostly in complex security scenarios. DOI: https://doi.org/10.52783/pst.353

show abstract

“…Sood et al 14 propose a two-stage network traffic anomaly detection system compatible with the ETSI-NFV standard 5G architecture. Their architecture involves reducing dimensionality to compress the sample size at the edge of 5G networks, along with a deep neural network (DNN) classifier for detecting traffic anomalies.…”

Section: Related Workmentioning

confidence: 99%

Dimensionality reduction for images of IoT using machine learning

Ali,

Wassif,

Bayomi

2024

Sci Rep

View full text Add to dashboard Cite

Sensors, wearables, mobile devices, and other Internet of Things (IoT) devices are becoming increasingly integrated into all aspects of our lives. They are capable of gathering enormous amounts of data, such as image data, which can then be sent to the cloud for processing. However, this results in an increase in network traffic and latency. To overcome these difficulties, edge computing has been proposed as a paradigm for computing that brings processing closer to the location where data is produced. This paper explores the merging of cloud and edge computing for IoT and investigates approaches using machine learning for dimensionality reduction of images on the edge, employing the autoencoder deep learning-based approach and principal component analysis (PCA). The encoded data is then sent to the cloud server, where it is used directly for any machine learning task without significantly impacting the accuracy of the data processed in the cloud. The proposed approach has been evaluated on an object detection task using a set of 4000 images randomly chosen from three datasets: COCO, human detection, and HDA datasets. Results show that a 77% reduction in data did not have a significant impact on the object detection task’s accuracy.

show abstract

Intrusion Detection Scheme With Dimensionality Reduction in Next Generation Networks

Cited by 28 publications

References 37 publications

Real-Time Clustering Based on Deep Embeddings for Threat Detection in 6G Networks

Real-Time Clustering Based on Deep Embeddings for Threat Detection in 6G Networks

Next-Generation Protection: Leveraging Federated Learning and Blockchain for Intrusion Detection in Smart Vehicle Network

Dimensionality reduction for images of IoT using machine learning

Contact Info

Product

Resources

About