Machine Learning has been steadily gaining traction for its use in Anomaly-based Network Intrusion Detection Systems (A-NIDS). Research into this domain is frequently performed using the KDD CUP 99 dataset as a benchmark. Several studies question its usability while constructing a contemporary NIDS, due to the skewed response distribution, nonstationarity, and failure to incorporate modern attacks. In this paper, we compare the performance for KDD-99 alternatives when trained using classification models commonly found in literature: Neural Network, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and K-Means. Applying the SMOTE oversampling technique and random undersampling, we create a balanced version of NSL-KDD and prove that skewed target classes in KDD-99 and NSL-KDD hamper the efficacy of classifiers on minority classes (U2R and R2L), leading to possible security risks. We explore UNSW-NB15, a modern substitute to KDD-99 with greater uniformity of pattern distribution. We benchmark this dataset before and after SMOTE oversampling to observe the effect on minority performance. Our results indicate that classifiers trained on UNSW-NB15 match or better the Weighted F1-Score of those trained on NSL-KDD and KDD-99 in the binary case, thus advocating UNSW-NB15 as a modern substitute to these datasets.
In software engineering, system modeling is the process of formulating a representation of a real system in an abstract way to understand its behavior. Software testing encourages reusing these models for testing purpose. This expedites the process of test case generation. UML structural and behavioral specification diagrams have been used by testing researchers for generation of test scenarios and test data.The aim of this survey is to improve the understanding of UML based testing techniques. We have focused on test case generation from the behavioral specification diagrams, namely sequence, state chart and activity diagrams. We classify the various research approaches that are based on formal specifications, graph theoretic, heuristic testing, and direct UML specification processing. We discuss the issues of test coverage associated with these approaches.
Concurrent programming is increasingly being used in many applications with the advent of multi-cores. The necessary support for execution of multi-threading is getting richer. Notwithstanding, a concurrent program may behave nondeterministically, it may result in different outputs with the same input in different runs.The aim of this study is to generate test sequences for concurrency from unified modelling language (UML) behavioral models such as sequence and activity diagrams. Generating exhaustive test cases for all concurrent interleaving sequences is exponential in size. Therefore, it is necessary to find adequate test cases in presence of concurrency to uncover errors due to, e.g., data race, synchronization and deadlocks. In order to generate adequate test cases a novel search algorithm, which we call concurrent queue search (CQS) is proposed. The CQS handles random nature of concurrent tasks. To generate test scenarios, a sequence diagram is converted into an activity diagram. An activity diagram encapsulates sequential, conditional, iterative and concurrent flows of the control. By the experimental results, it was observed that test sequences generated by CQS algorithm are superior as compared to DFS and BFS search algorithms.
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.