Deep learning approach to security enforcement in cloud workflow orchestration

Kassabi, Hadeel T. El; Serhani, Mohamed Adel; Masud, Mohammad Mehedi; Shuaib, Khaled; Khalil, Khaled M.

doi:10.1186/s13677-022-00387-2

Cited by 7 publications

(3 citation statements)

References 41 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of Reference 25 offer a novel feature modeling technique that improves anomaly identification for a model that considers unsupervised static and dynamic properties. Furthermore, it reduces the dimensionality of the data, allowing for better characterization of workflow processes and, as a result, prediction of assaults.…”

Section: Review Of Literaturementioning

confidence: 99%

Transforming data‐intensive workflows: A cutting‐edge multi‐layer security and quality aware security framework

Aljohani

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe data‐intensive workflow application executes tasks on edge servers and cloud platforms in a heterogeneous big‐data computing environment. Cloud and edge servers are vulnerable to node attacks and malicious links due to their wireless connections. Thus, detecting and mitigating rogue nodes in edge server communication environments during workflow execution is crucial. In today's workflow execution landscape, there is a rising emphasis on resolving Quality of Service (QoS) and security concerns within homogeneous execution settings. Workflow execution on diverse computing platforms has received limited research. We are developing an edge‐cloud‐specific Multi‐Layer Security and Quality‐Aware (MLSQA) framework to solve research issues in this area. Node attacks are detected via reputation‐based security features in the MLSQA framework, whereas link attacks are detected using machine learning. A unique trade‐off metrics technique optimizes workflow security and QoS parameters, reducing energy usage and makespan. In addition, a fault‐tolerant, energy‐efficient job offloading technique is described in detail to improve the system's resilience to errors. The experiment is conducted using complex (i.e., memory and CPU intensive) scientific procedures with intermediate job dependencies, namely Inspiral workflow. The MLSQA framework excels in threat detection, demonstrating lower false alarms, reduced energy consumption, and quicker implementation than the recent secure workflow execution architecture.

show abstract

Section: Review Of Literaturementioning

confidence: 99%

Transforming data‐intensive workflows: A cutting‐edge multi‐layer security and quality aware security framework

Aljohani

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…AI and machine learning can be employed to analyze large datasets, predict workflow patterns, and optimize resource allocation [19][20]. These techniques can identify patterns of inefficiency and provide personalized recommendations.…”

Section: ⅱ Related Workmentioning

confidence: 99%

Machine Learning-Based Work Efficiency Monitoring Method for Student Supervisor

2023

J Multimed Inf Syst

View full text Add to dashboard Cite

As student supervisor workloads increase, ensuring efficient support is challenging. A novel machine learning method using clustering analysis is proposed to gain insights into time allocation and identify optimization opportunities. Specifically, a covariance distance measure analysis approach is presented for characterizing the closeness of data items in multi-dimensional cluster analysis through efficient distance measuring. The membership degree of each sample point is first determined concerning class characteristics through the fuzzy c-means approach, which involves first assigning weights to data items. Then, the membership degree is used to determine the degree of dissimilarity between the samples. Finally, the covariance distance measurement between sample points is used as the second optimization criterion to distinguish between data types, and the optimal solution is calculated iteratively by alternating fixed variables to optimize the clustering metric and the distance measurement learning parameters and produce more accurate clustering results. The experimental findings on datasets demonstrate that the proposed approach outperforms benchmarks in terms of clustering accuracy. Therefore, the high clustering accuracy empowers the student supervisor to make informed decisions about time allocation, allowing them to optimize their efforts and resources.

show abstract

“…Cloud Security Automation and Orchestration Automation and orchestration technologies are being used to streamline security processes, such as incident response and threat remediation [192].…”

mentioning

confidence: 99%

Security challenges in cloud computing: A comprehensive analysis

Janet Julia Ang'udi

2023

World J. Adv. Eng. Technol. Sci.

View full text Add to dashboard Cite

The security issues surrounding cloud computing, a quickly developing technology that is now essential to both personal and business computing, are thoroughly examined in this study. Cloud computing presents serious security risks that require careful attention, despite its many advantages such as scalability, cost-effectiveness, and flexibility. In-depth discussions of a number of important security topics are covered in this paper, including network security, access control, data breaches, legal and regulatory framework compliance, and new threats and vulnerabilities. The paper illuminates the complexities of data and application security in the cloud environment by thoroughly examining these subjects. The study also looks at actual case studies to show how security breaches in cloud computing affect things and how to fix them. The study intends to offer insightful analyses of security challenges with practical implications by examining these cases and providing lessons learned from incidents that have happened in various cloud computing scenarios. Our comprehension of the complex nature of security threats and the tactics used to counter and mitigate them is improved by looking closely at these cases. This study looks into the potential benefits of cloud security enhancements from emerging technologies like artificial intelligence and machine learning, in addition to identifying existing challenges. The research investigates the potential benefits of these technologies in terms of automated security responses, adaptive access controls, and proactive threat detection. Cloud environments may be able to improve their security posture against new and sophisticated threats by utilizing the powers of AI and machine learning. Furthermore, by projecting future trends and challenges in cloud security, this paper offers a forward-looking view of the changing field. Comprehending these possible obstacles is crucial to creating proactive and flexible security approaches that can successfully tackle the ever-changing landscape of cloud computing. This paper's ultimate objective is to offer insightful information about practical approaches and industry best practices for safeguarding cloud environments. Organizations can navigate the complexity of the cloud landscape while protecting their data and applications from the ever-evolving threat landscape by striking a balance between the enormous potential of cloud computing and the necessity of maintaining strong security measures.

show abstract

Deep learning approach to security enforcement in cloud workflow orchestration

Cited by 7 publications

References 41 publications

Transforming data‐intensive workflows: A cutting‐edge multi‐layer security and quality aware security framework

Transforming data‐intensive workflows: A cutting‐edge multi‐layer security and quality aware security framework

Machine Learning-Based Work Efficiency Monitoring Method for Student Supervisor

Security challenges in cloud computing: A comprehensive analysis

Contact Info

Product

Resources

About