F. Giannakas, V. Kouliaridis, G. Kambourakis, A closer look at machine learning effectiveness in Android malware detection, Information, pp. 1-25, 2022, MDPI, https://www.mdpi.com/journal/inform...
Nowadays, with the increasing usage of Android devices in daily life activities, malware has been increasing rapidly, putting peoples' security and privacy at risk. To mitigate this threat, several researchers have proposed different methods to detect Android malware. Recently, machine learning based models have been explored by a significant mass of researchers checking for Android malware. However, selecting the most appropriate model is not straightforward, since there are several aspects that must be considered. Contributing to this domain, the current paper explores Android malware detection from diverse perspectives; this is done by optimizing and evaluating various machine learning algorithms. Specifically, we conducted an experiment for training, optimizing, and evaluating 27 machine learning algorithms, and a Deep Neural Network (DNN). During the optimization phase, we performed hyperparameter analysis using the Optuna framework. The evaluation phase includes the measurement of different performance metrics against a contemporary, rich dataset, to conclude to the most accurate model. The best model was further interpreted by conducting feature analysis, using the Shapley Additive Explanations (SHAP) framework. Our experiment results showed that the best model is the DNN consisting of 4 layers (two hidden), using the Adamax optimizer, as well as the Binary Cross-Entropy (loss), and the Softsign activation functions. The model succeeded 86% prediction accuracy, while the balanced accuracy, the F1-score, and the ROC-AUC metrics were at 82%.
F. Giannakas, A. Papasalouros, G. Kambourakis, S. Gritzalis, A comprehensive cybersecurity learning platform for elementary education, Information Security Journal: A Global Perspective, Vol. 28, No. 3, pp. 81-106, 2019, Taylor and Francis, https://www.tandfonline.com/toc/uis...
For elementary students, security and privacy education is anticipated to be more joyful when the knowledge is delivered in the form of a digital game-based learning activity. This paper details on the development of a novel learning platform that comprises a web-based Learning Content Management Systems (LCMS) and a mo-
bile client application (app) for educating and raising young learners' awareness on basic cybersecurity and privacy issues. The app, which comprises a suite of quick games, can be played either in standalone or in client/server mode and it is especially destined to elementary students. Further, due to the anytime and anywhere
characteristics of the app, it can be experienced as a classroom or an outdoor learning activity. Contrary to analogous studies found in the literature so far, during the design phase of the app, our focus was not solely on its technological aspects, but we uniformly paid special attention to the educational factor by applying the
Attention, Relevance, Confidence, and Satisfaction (ARCS) model of motivation. A preliminary evaluation of the app, including learning eectiveness, usability, and user's satisfaction was conducted with 52 elementary-aged students. Among others, the results show that the interaction with the app significantly increases the mean
performance of the participants by almost 20%.
F. Giannakas, G. Kambourakis, A. Papasalouros, S. Gritzalis, A critical review of 13 years of Mobile Game-based Learning, Educational Technology Research and Development, Vol. 66, pp. 341-384, 2018, Springer, http://rdcu.be/BdTM
, indexed in SCI-E, IF = 2.115
With the increasing popularity of smartphones and tablets, Game-Based Learning (GBL) is undergoing a rapid shift to mobile platforms. This transformation is driven by mobility, wireless interfaces, and built-in sensors that these smart devices offer in order to enable blended and context-sensitive mobile learning (m-Learning) activities. Thus, m-Learning is becoming more independent and ubiquitous (u-Learning). In order to identify and analyze the main trends and the future challenging issues involved in designing mGBL learning strategies, as well as to bring to the foreground important issues pertaining to mobile and context-aware ubiquitous GBL, the work at hand conducts a comprehensive survey of this particular area. Specifically, it introduces and applies a six-dimensional framework consisted of Spatio-temporal, Collaboration/Social, Session, Personalization, Data security & privacy, and Pedagogy, with the aim of scrutinizing the contributions in the field of mGBL published from 2004 to 2016. It was found that the transition to mGBL presents several difficulties, and therefore cannot be conceived as a simple and quick modification of existing GBL solutions. In this respect, this work is anticipated to foster the development of well-designed solutions that are intensive not only in their technological aspect, but in pedagogical qualities as well.
F. Giannakas, G. Kambourakis, A. Papasalouros, S. Gritzalis, Security education and awareness for K-6 going mobile, International Journal of Interactive Mobile Technologies, Vol. 10, No. 2, pp. 41-48, 2016, International Association of Online Engineering, http://www.i-jim.org
Nowadays, due to the widespread participation of elementary school children in cyberspace activities, basic cybersecurity education and awareness is deemed necessary. Within this context, knowledge acquisition in this timely and important field has greater chances to be more fruitful when the learner is properly motivated. Also, it is anticipated to be more joyful when knowledge is acquired in the form of a digital game-based activity. The paper at hand discusses the development of a novel mobile app called CyberAware, destined to cybersecurity education and awareness. At present, the game is designed for K-6 children in order to support either or both formal or informal learning. Additionally, due to its mobile characteristics, the game can be experienced as an outdoor or classroom activity. Finally, opposite to similar studies found in the literature so far, our attention is not solely drawn to game’s technological aspects but equally to the educational factor. This is achieved through the consideration and use of the ARCS motivational model already from the game's design phase.
F. Giannakas, G. Kambourakis, S. Gritzalis, CyberAware: A Mobile Game-based app for Cybersecurity Education and Awareness, IMCL 2015 International Conference on Interactive Mobile Communication, Technologies and Learning, 2015, IEEE CPS Conference Publishing Services, http://www.imcl-conference.org/imcl...
Nowadays, basic cybersecurity education and
awareness is deemed necessary, even for children as young as elementary school-aged. If knowledge on this topic is delivered in the form of a digital game-based activity, then it has greater
chances of being more joyful and efficient. The paper at hand discusses the development of a novel mobile app called CyberAware, destined to cybersecurity education and awareness. At
present, the game is designed for K-6 aged children and can be used to support either or both formal or informal learning. Also, due to its mobile nature, it can be experienced as an outdoor or classroom activity. Opposite to similar studies found in the literature so far, our attention is not solely drawn to game's technological aspects but equally to the educational factor.
F. Giannakas, Didactical and Pedagogical use of I.C.T. at Primary School with S.R.E.P : Understand, communicate, seek, collaborate and implement, 3rd Pan-Hellenic Conference "Integration and Use of ICTs to the Education Process", 2013
F. Giannakas, K. Papanikolaou, Interaction Analysis at synchronous educational environments, 7th Pan-Hellenic Conference with International participation, 2010, http://korinthos.uop.gr/~hcicte10/
F. Giannakas, An alternative proposal with the design of electronic games for the teaching of Multimedia-Networks lesson to the Secondary Education, 5th Pan-Hellenic Conference at the Didactic of Informatics, 2010, http://hermes2.di.uoa.gr:8080/didin...