Currently, expert systems and applied machine learning algorithms are widely used to automate network intrusion detection. In critical infrastructure applications of communication technologies, the interaction among various industrial control systems and the Internet environment intrinsic to the IoT technology makes them susceptible to cyber-attacks. Given the existence of the enormous network traffic in critical Cyber-Physical Systems (CPSs), traditional methods of machine learning implemented in network anomaly detection are inefficient. Therefore, recently developed machine learning techniques, with the emphasis on deep learning, are finding their successful implementations in the detection and classification of anomalies at both the network and host levels. This paper presents an ensemble method that leverages deep models such as the Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and a meta-classifier (i.e., logistic regression) following the principle of stacked generalization. To enhance the capabilities of the proposed approach, the method utilizes a two-step process for the apprehension of network anomalies. In the first stage, data pre-processing, a Deep Sparse AutoEncoder (DSAE) is employed for the feature engineering problem. In the second phase, a stacking ensemble learning approach is utilized for classification. The efficiency of the method disclosed in this work is tested on heterogeneous datasets, including data gathered in the IoT environment, namely IoT-23, LITNET-2020, and NetML-2020. The results of the evaluation of the proposed approach are discussed. Statistical significance is tested and compared to the state-of-the-art approaches in network anomaly detection.
The Internet of Things (IoT) appliances often expose sensitive data, either directly or indirectly. They may, for instance, tell whether you are at home right now or what your long or short-term habits are. Therefore, it is crucial to protect such devices against adversaries and has in place an early warning system which indicates compromised devices in a quick and efficient manner. In this paper, we propose time window embedding solutions that efficiently process a massive amount of data and have a low-memory-footprint at the same time. On top of the proposed embedding vectors, we use the core anomaly detection unit. It is a classifier that is based on the transformer’s encoder component followed by a feed-forward neural network. We have compared the proposed method with other classical machine-learning algorithms. Therefore, in the paper, we formally evaluate various machine-learning schemes and discuss their effectiveness in the IoT-related context. Our proposal is supported by detailed experiments that have been conducted on the recently published Aposemat IoT-23 dataset.
In this paper, biometric methods for contactless and unrestricted access control for mobile devices are proposed. The major contribution of this paper are palmprint and knuckles feature extraction methods dedicated for the mobile contactless biometrics. We use texture maskbased features for the palmprint. For the knuckles, we use Probabilistic Hough Transform and Speeded Up Robust Features as well as the 3-step classification methodology. We prove the efficiency of the presented methods by reporting promising results.
Quality Requirements (QRs) are a key artifact needed to ensure the quality and success of a software system. Despite their importance, QRs rarely get the same degree of attention as their functional counterpart in Agile Software Development (ASD) projects. Moreover, crucial information that can be obtained from software development repositories (e.g., JIRA, GitHub,…) is not fully exploited, or is even neglected, in QR elicitation activities. In this work, we present a data-driven tooled approach for the semi-automatic generation and documentation of QRs in the context of ASD. The approach is based on the declaration of thresholds over quality-related issues, whose violation triggers user-defined alerts. These alerts are used to browse a catalog of QR patterns that are presented to the ASD team by means of a dashboard that implements several analysis techniques. Once selected, the patterns generate the QRs, which are documented and stored in the product backlog. The full approach is implemented via a configurable platform. Over the course of one year, four companies differing in size and profile followed this approach and deployed the platform in their premises to semi-automatically generate QRs in several projects. We used standardized measurement instruments to elicit the perception of 22 practitioners regarding their use of the tool. The quantitative and qualitative analyses yielded positive results; i.e., the practitioners' perception with regard to the tool's understandability, reliability, usefulness, and relevance was positive. We conclude that the results show potential for future adoption of data-driven elicitation of QRs in agile companies and encourage other practitioners to use the presented tool and adopt it in their companies.
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.