Upon receiving risk descriptions, based on theĭesigned meta-rules, the AC system adapts the security rules to allowĭistributed denial of service (DDoS) attacks on the Internet in general and particularly in Grid computing environment has become a visible issue in computer networks and communications. Coming to security,Ī risk-adaptive Access Control (AC) model based on Attribute-BasedĪccess Control (ABAC) is developed considering hierarchical
In addition, an ontology is designed and developed toĮxtract safet knowledge in a computer-readable way. Proposed that exploits an automated risk assessment process that isĭeveloped considering the commonly adopted risk assessment techniques in Starting with safety, a run-time risk management methodology is In this thesis, the security and safety of the risk-prone SWEs are The safety-related context in each situation. Should allow the treatment of the risks when necessary by adapting to This is an advantage to protect persons' safety, the security policies Technology provides the chance to acquire ambient and monitoring data toīe exploited to identify and treat the risks related to safety. Sensitive and critical resources in the SWEs. And hence new approaches should be proposed to protect the The IoT technology, SWEs become more and more vulnerable to the security On one hand, as more devices are getting integrated in With all new technologies, SWEs introduce various issues and The appearance of Industry 4.0 and Smart Work Environments (SWEs). (IoT) which has a direct or indirect effect on how safety and securityĪs an emerging technology, IoT, has provided a promising opportunity in
Security as dependent aspects and co-engineering them together asĬyber-security is highlighted with the advent of Internet of Things Safety and security are two risk-driven aspects that are By comparing our work to the existing research works, the accuracy of the defect determination was significantly improved which is approximately 85% and 79%, respectively.Ĭo-Engineering Safety and Security in Risk-Prone Smart The average Accuracy (AC) of our suggested model is ~90%. In the second classification, the results showed that both Precision (PR) and Recall (RE) are approximately 90% for the XGBoost algorithm. The average Accuracy (AC) of our proposed model is ~89% which is superb and enough good. In the first classification, the results showed that both Precision (PR) and Recall (RE) are After applying the machine learning models, we generated a confusion matrix for identification of the model performance. For the proposed work, the UNWS-np-15 dataset was extracted from the GitHub repository and Python was used as a simulator. To access the research proposed a complete framework for DDoS attacks prediction. For this purpose, used Random Forest and XGBoost classification algorithms. This paper, used a machine learning approach for DDoS attack types classification and prediction. It is necessary to work with the latest dataset to identify the current state of DDoS attacks. In the existing research study, the author worked on an old KDD dataset. These attacks take advantage of specific limitations that apply to any arrangement asset, such as the framework of the authorized organization’s site. Distributed network attacks are referred to, usually, as Distributed Denial of Service (DDoS) attacks.
0 kommentar(er)
