Orchestration of data-intensive pipeline in 5G-enabled Edge Continuum

Anisetti, Marco; Berto, Filippo; Banzi, Massimo

doi:10.1109/services55459.2022.00025

Cited by 9 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When building a machine learning model, feature selection is used to narrow down the data points to a manageable collection. Improving the model's accuracy and decreasing the computational cost of training it make this a crucial step in the model-building process [24]. To overcome the limitations of logistic regression model, enhanced logistic regression model is designed in this research.…”

Section: Fig 1: Malware Analysis In Cloudmentioning

confidence: 99%

Intellectual Feature Ranking Model with Correlated Feature Set based Malware Detection in Cloud environment using Machine Learning

Rao,

Jain,

Gangadhar

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Malware detection for cloud systems has been studied extensively, and many different approaches have been developed and implemented in an effort to stay ahead of this ever-evolving threat. Malware refers to any programme or defect that is designed to duplicate itself or cause damage to the system's hardware or software. These attacks are designed specifically to cause harm to operational systems, but they are invisible to the human eye. One of the most exciting developments in data storage and service delivery today is cloud computing. There are significant benefits to be gained over more conventional protection methods by making use of this fast evolving technology to protect computer-based systems from cyber-related threats. Assets to be secured may reside in any networked computing environment, including but not limited to Cyber Physical Systems (CPS), critical systems, fixed and portable computers, mobile devices, and the Internet of Things (IoT). Malicious software or malware refers to any programme that intentionally compromises a computer system in order to compromise its security, privacy, or availability. A cloud-based intelligent behavior analysis model for malware detection system using feature set is proposed to identify the ever-increasing malware attacks. The suggested system begins by collecting malware samples from several virtual machines, from which unique characteristics can be extracted easily. Then, the malicious and safe samples are separated using the features provided to the learning-based and rule-based detection agents. To generate a relevant feature set for accurate malware detection, this research proposes an Intellectual Feature Ranking Model with Correlated Feature Set (IFR-CFS) model using enhanced logistic regression model for accurate detection of malware in the cloud environment. The proposed model when compared to the traditional feature selection model, performs better in generation of feature set for accurate detection of malware.

show abstract

Section: Fig 1: Malware Analysis In Cloudmentioning

confidence: 99%

Intellectual Feature Ranking Model with Correlated Feature Set based Malware Detection in Cloud environment using Machine Learning

Rao,

Jain,

Gangadhar

et al. 2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Moreover, the system is equipped with 5G capabilities, enabling it to achieve remarkable data throughput and minimal communication delay. This empowers sensors and devices to seamlessly exchange data in realtime between clients and servers, especially when deployed within a data-intensive 5G framework as exemplified in [17]. This advancement enhances system efficiency compared to earlier iterations where immediate connectivity was restricted to private networks with high-speed links.…”

Section: Introductionmentioning

confidence: 99%

Zero-Day Guardian: A Dual Model Enabled Federated Learning Framework for Handling Zero-Day Attacks in 5G Enabled IIoT

Verma,

Bharot,

Breslin

et al. 2024

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

5G emerges as the bedrock for the Industrial Internet of Things (IIoT), it facilitates the seamless, low-latency fusion of artificial intelligence and cloud computing, thereby fortifying the entire industrial procedure within a framework of smart and intelligent IIoT ecosystems. Concurrently, the continuously changing landscape of cybersecurity threats in the realm of the Internet of Things (IoT) is giving rise to unparalleled security complexities. These challenges are particularly pronounced in the context of zero-day attacks, and integration of 5G technology further exacerbates the intricacy of the situation. Thus this paper introduces a cutting-edge 5G-enabled framework for cyberthreat detection leveraging Federated Learning (FL) without the need for data sharing. It employs a dual Autoencoder (AE) based model. Distinctly, our model utilizes two synchronized AEs for each client, integral to FL mechanism. While one AE evaluates the IIoT environment based on normal network patterns, another focuses on attack scenarios. For decisive threat assessment, the system uses the capabilities of a one-class SVM classifier with AEs. Furthermore, our method ensures a synergistic blend of selflearning and collaborative learning by implementing a polling mechanism between overarching AE classifier and those tailored to individual client data and counters zero-day threats and out performs traditional AI/ML techniques.

show abstract

“…The proposed architecture integrates an adequate number of layers, trained and tested on benchmark data set. Further, the system is 5G enabled, thus, providing high throughput and low latency and can make it feasible for sensors and devices to share data in real-time when deployed on a 5G data-intensive solution such as the one in [15]. This makes the system more efficient than previous ones, in which real-time connectivity is only possible when the devices are located on private networks with high-speed connectivity.…”

Section: Introductionmentioning

confidence: 99%

A Multilayer Deep Learning Approach for Malware Classification in 5G-Enabled IIoT

Ahmed

Anisetti

Ahmad

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

5G is becoming the foundation for the Industrial Internet of Things (IIoT) enabling more effective lowlatency integration of artificial intelligence and cloud computing in a framework of a smart and intelligent IIoT ecosystems enhancing the entire industrial procedure. However, it also increases the functional complexities of the underlying control system, and introduce new powerful attacks vectors leading to severe security and data privacy risks. Malware attacks are starting targeting weak but highly connected IoT devices showing the importance of security and privacy in this scenario. This paper designs a 5G-enabled system, consisted in a deep learning-based architecture aimed to classify malware attacks on the IIoT. Our methodology is based on an image representation of the malware and a Convolutional Neural Networks (CNNs) that is designed to differentiate various malware attacks. The proposed architecture extracts complementary discriminative features by combining multiple layers achieving 97% of accuracy.

show abstract

Orchestration of data-intensive pipeline in 5G-enabled Edge Continuum

Cited by 9 publications

References 20 publications

Intellectual Feature Ranking Model with Correlated Feature Set based Malware Detection in Cloud environment using Machine Learning

Intellectual Feature Ranking Model with Correlated Feature Set based Malware Detection in Cloud environment using Machine Learning

Zero-Day Guardian: A Dual Model Enabled Federated Learning Framework for Handling Zero-Day Attacks in 5G Enabled IIoT

A Multilayer Deep Learning Approach for Malware Classification in 5G-Enabled IIoT

Contact Info

Product

Resources

About