Software-Defined Networking (SDN) is a promising technology for the future Internet. However, the SDN paradigm introduces new attack vectors that do not exist in the conventional distributed networks. This paper develops a hybrid Intrusion Detection System (IDS) by combining the Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). The proposed model is capable of capturing the spatial and temporal features of the network traffic. Two regularization techniques i.e., L2 Regularization (L2 Reд.) and dropout method are used to overcome with the overfitting problem. The proposed method improves the intrusion detection performance of zero-day attacks. The InSDN dataset -the most recent dataset for SDN networks is used to test and evaluate the performance of the proposed model. The results indicate that integrating the CNN with LSTM improves the intrusion detection performance and achieves an accuracy of 96.32%. The estimated accuracy is higher than the accuracy of each individual model. In addition, it is established that the regularization techniques improves the performance of the CNN algorithms in detecting new intrusions when compared to the standard CNN. The findings of this study facilitates the development of robust IDS systems for SDN environment.
The number of web applications for both personal and business use will continue to increase. The popularity of web applications has grown, increasing the need to estimate Quality of Experience for web applications (Web QoE). Web QoE helps providers to understand how their end-users perceive quality and point towards areas to improve. Waiting time has been proven to have a significant influence on user satisfaction. Most studies in the field of Web QoE have focused on modelling Web QoE for the user's first interaction with the application, e.g., the waiting time for the first page load to complete. This does not include a user's subsequent interactions with the application. Users keep interacting with the application beyond the first page load resulting in an experience that consists of a series of waiting times. In this study, we have chosen web maps as a use case to investigate how to measure waiting time for a user's interactions across a web browsing session, and to measure the correlation between waiting time and user-reported perceived quality. We provide a short survey of existing Web QoE estimation metrics and models. We then propose two new measures: interactive Load Time (iLT) and Total Completed interactive Load (TCiL) to establish the waiting time associated with a web application user's interactions. A subjective study confirms a logarithmic relationship for interactive web application sessions between iLT and perceived quality. We compare the correlation between QoE for iLT and the state of the art, non-interactive equivalent, Page Load Time (PLT)/Waiting Time. We demonstrate how the iLT/QoE fitting curve deviates from PLT/QoE. The number of clicks in completing tasks and TCiL are explored to explain the connections between user's interactions behaviour and the perceived quality. INDEX TERMS Web QoE, interactive QoE, quality measurement, quality metrics, time metrics, waiting time, iLT, TCiL.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.