An Assurance Framework and Process for Hybrid Systems

Anisetti, Marco; Ardagna, Claudio Agostino; Bena, Nicola; Damiani, Ernesto

doi:10.1007/978-3-030-90428-9_4

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, it was discovered that selecting features for high-dimensional datasets in parallel could lessen the computing load of logistic regression [21]. Although it does a reasonable job of classifying data, logistic regression suffers from a lack of computing efficiency [22]. This is because it typically uses an optimization technique belonging to the hill-climbing Newton family, such as Newton-Raphson and its variants and extensions, to arrive at an estimate.…”

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

“…As an industry adopts more and more IIoT based systems, it will become increasingly necessary to use an efficient system control strategy. Assurance has been identified as a suitable way to control a target system against security concerns [13], computing, for instance, a risk indicator [14]. More particularly, the industry must be capable of confidently identifying IIoT systems to prevent the use of miscreant or unreliable devices and systems.…”

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

“…The advent of Edge Computing has changed the way a service composition can be deployed, allowing for instance to better support real-time applications via low latency [1] and in general a better placement of services to fulfill specific QoS requests [2], [3]. Despite being physically separated from the Cloud, the Edge heavily depends on it to execute resourcehungry tasks, since computational power available on Edge nodes decreases the farthest they are from the Cloud.…”

Section: Introductionmentioning

confidence: 99%

QoS-Aware Deployment of Service Compositions in 5G-Empowered Edge-Cloud Continuum

Anisetti,

Berto,

Bondaruc

2023

2023 IEEE 16th International Conference on Cloud Computing (CLOUD)

Self Cite

View full text Add to dashboard Cite

Nowadays, modern service compositions are increasingly adopted in critical scenarios where advanced Quality of Services (QoS) such as low latency, security, and privacy are fundamental. The landing platforms for the deployment of such compositions are progressively becoming capable to offer capabilities that support such advanced QoS requests (e.g., low latency via 5G network slice) spanning the Edge-Cloud Continuum. Actual deployment solutions focus mainly on resource allocation (i.e., CPU, memory, and storage), falling short of addressing advanced QoS and unleashing the true potential of the Edge-Cloud Continuum. In this paper, we present an automatic QoSaware deployment solution for composed services in the Edge-Cloud Continuum. It compares QoS requests on the service composition with the capabilities of a given continuum in order to find, generate and execute suitable deployment recipes. Our preliminary experimental evaluation demonstrates the feasibility of our solution in a realistic scenario.

show abstract

An Assurance Framework and Process for Hybrid Systems

Cited by 4 publications

References 25 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

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

QoS-Aware Deployment of Service Compositions in 5G-Empowered Edge-Cloud Continuum

Contact Info

Product

Resources

About