Abstract
Information systems depend on security mechanisms to detect and respond to cyber-attacks. One of the most frequent attacks is the Distributed Denial of Service (DDoS): it impairs the performance of systems and, in the worst case, leads to prolonged periods of downtime that prevent business processes from running normally. To detect this attack, several supervised Machine Learning (ML) algorithms have been developed and companies use them to protect their servers. A key stage in these algorithms is feature pre-processing, in which, input data features are assessed and selected to obtain the best results in the subsequent stages that are required to implement supervised ML algorithms. In this article, an innovative approach for feature selection is proposed: the use of Visibility Graphs (VGs) to select features for supervised machine learning algorithms used to detect distributed DoS attacks. The results show that VG can be quickly implemented and can compete with other methods to select ML features, as they require low computational resources and they offer satisfactory results, at least in our example based on the early detection of distributed DoS. The size of the processed data appears as the main implementation constraint for this novel feature selection method.

Abstract

Abstract
Vulnerability scanning tools are essential in detecting systems weaknesses caused by vulnerabilities in their components or wrong configurations. Corporations may use these tools to assess a system in advance and fix its vulnerabilities, thus preventing or mitigating the impact of real attacks. A set of these tools are organized by plugins, each intended to check a specific vulnerability, such as the case of the Tsunami Security Scanner tool released in 2020 by Google. Multiple plugins for this tool were proposed in a community-based approach and thus, it is important for the users and research community to have these plugins in a framework consistently categorized across multiple sources and types. This paper proposes a comprehensive taxonomy for all the 61 plugins available, hierarchically sorted into 2 main categories, 4 categories, 4 subcategories, and 7 types. An analysis and a discussion on statistics by categories and types over time are also provided. The analysis shows that, so far, there are 4 main contributors, being Google, Community, Facebook, and Govtech. The Google source is still the top contributor counting 39 out of 61 plugins and the highest number of plugins available are in the RCE subcategory. The plugins available are mainly focused on critical and high vulnerabilities.

Abstract
Cybersecurity skills are of utmost importance to prevent or mitigate the impact of cyberattacks. In higher education, there are graduations related to Information Technology (IT), where students are expected to develop technical skills, including cybersecurity. Thus, it is relevant to assess students' cybersecurity awareness regarding cybersecurity hygiene and cyber threats when they start their academic studies and to verify whether there are context-dependent differences. This paper presents the results of an assessment regarding the cybersecurity awareness level of 110 first-year students from computer science graduations from two different countries, Poland and Portugal. The assessment was designed as a survey divided into the following two main groups of questions: (1) awareness regarding cybersecurity hygiene and (2) awareness regarding major cyber threats considered in the European Union Agency for Cybersecurity (ENISA) 2021 cyber threat report. The survey results show that Polish and Portuguese students present different self-perceptions and knowledge regarding cybersecurity hygiene and knowledge of cybersecurity. In these areas, Polish students are generally more confident than Portuguese students. Also, Polish students presented better scores around 70%, against the ones obtained by the Portuguese students, scoring around 58%.

Abstract
Technology has enabled many devices to exchange huge amounts of data and communicate with each other as Edge Intelligence in Smart Cities (EISC), as a result of rapid technological advancements. When dealing with personal data, it is paramount to ensure that it is not disclosed and that there is no disclosure of any confidential information. In recent decades, academics and industry have spent considerable time and energy discussing security and privacy. Other systems, known as intrusion detection systems, are required to breach firewalls, antivirus software, and other security equipment to provide complete system security in smart operation systems. There are three aspects to an intrusion detection system: the intrusion detection method, the architecture, and the intrusion response method. In this study, we combined linear correlation feature selection methods and cross-information. The database used in this article is KDD99. This paper examines applying two feature selection methods in predicting attacks in intrusion detection systems based on INTERACT and A multilayer perceptron (MLP). Since the number of records associated with each attack type differs, one of our suggestions is to continue using data balancing techniques. As a result, the number of records associated with each type of network status becomes closer together. The results in the categories can also be improved using information synthesis methods, such as majority voting.

Abstract