Εκπαίδευση - Σπουδές

Διδακτορική Διατριβή, Επαλήθευση Συγγραφέα (Επιβλέπων καθηγητής, Σταματάτος Ευστάθιος).

Μεταπτυχιακό, Τεχνολογίες και Διαχείριση Πληροφοριακών και Επικοινωνιακών Συστημάτων, Τμήμα Μηχανικών Πληροφοριακών
& Επικοινωνιακών Συστημάτων, Πανεπιστήμιο Αιγαίου.

Πτυχίο Φυσικής, Τμήμα Φυσικής, Πανεπιστήμιο Ιωαννίνων.

Ερευνητικά Ενδιαφέροντα

Εξόρυξη κειμένων
Ευφυής ανάκτηση πληροφορίας
Επεξεργασία φυσικής γλώσσας
Μηχανική μάθηση

Διδασκαλία

Φροντιστήριο του μαθήματος "Φυσική" (Α' Εξάμηνο)

Φροντιστήριο του μαθήματος "Πιθανότητες και Στατιστική" (Β'Εξάμηνο)

Δημοσιεύσεις σε Διεθνή Περιοδικά (Journals)


Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or mass reproduced without the explicit permission of the copyright holder.


V. Kouliaridis, G. Kambourakis, D. Geneiatakis, N. Potha, Two anatomists are better than one: Dual-level Android malware detection, Symmetry, Vol. 12, No. 7, 2020, MDPI, https://www.mdpi.com/2073-8994/12/7..., indexed in SCI-E, IF = 2.645
 

Abstract
The openness of the Android operating system and its immense penetration into the market makes it a hot target for malware writers. This work introduces Androtomist, a novel tool capable of symmetrically applying static and dynamic analysis of applications on the Android platform. Unlike similar hybrid solutions, Androtomist capitalizes on a wealth of features stemming from static analysis along with rigorous dynamic instrumentation to dissect applications and decide if they are benign or not. The focus is on anomaly detection using machine learning, but the system is able to autonomously conduct signature-based detection as well. Furthermore, Androtomist is publicly available as open source software and can be straightforwardly installed as a web application. The application itself is dual mode, i.e., fully automated for the novice user and configurable for the expert one. As a proof-of-concept, we meticulously assess the detection accuracy of Androtomist against three different popular malware datasets and a handful of machine learning classifiers. We particularly concentrate on the classification performance achieved when the results of static analysis are combined with dynamic instrumentation vis-`a-vis static analysis only. Our study also introduces an ensemble approach by averaging the output of all base classification models per malware instance separately, and provides a deeper insight on the most influencing features regarding the classification process. Depending on the employed dataset, for hybrid analysis, we report notably promising to excellent results in terms of the accuracy, F1, and AUC metrics.

N. Potha, V. Kouliaridis, G. Kambourakis, An Extrinsic Random-based Ensemble Approach for Android Malware Detection, Connection Science, 2020, Taylor and Francis, https://www.tandfonline.com/toc/cco..., indexed in SCI-E, IF = 1.042
 

Abstract
Malware detection is a fundamental task and associated with significant applications in humanities, cybersecurity, and social media analytics. In some of the relevant studies, there is substantial evidence that heterogeneous ensembles can provide very reliable solutions, better than any individual verification model. However, so far, there is no systematic study of examining the application of ensemble methods in this task. This paper introduces a sophisticated Extrinsic Random-based Ensemble(ERBE) method where in a predetermined set of repetitions, a subset of external instances (either malware or benign) as well as classification features are randomly selected, and an aggregation function is adopted to combine the output of all base models for each test case separately. By utilising static analysis only, we demonstrate that the proposed method is capable of taking advantage of the availability of multiple external instances of different size and genre. The experimental results in AndroZoo benchmark corpora verify the suitability of a random-based heterogeneous ensemble for this task and exhibit the effectiveness of our method, in some cases improving the hitherto best reported results by more than 5%.

[3]
N. Potha, E. Stamatatos, Improving author verification based on topic modeling, Journal of the Association for Information Science and Technology , Vol. 70, No. 10, pp. 1074-1088, 2019, Wiley Online Library, https://doi.org/10.1002/asi.24183
[4]
N. Potha, Improved Algorithms for Extrinsic Author Verification, Knowledge and Information Systems, 2019, Knowledge and Information Systems, Springer. ,
[5]
N. Potha, M. Maragoudakis, D. Lyras, A Biology-Inspired, Data Mining Framework for Extracting Patterns in Sexual Cyberbullying Data, Knowledge-Based Systems, 2016, Elsevier, (to_appear), http://dx.doi.org/10.1016/j.knosys...., indexed in SCI-E, IF = 2.947

Επιστημονικά Συνέδρια (Conferences)


Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or mass reproduced without the explicit permission of the copyright holder.


V. Kouliaridis, N. Potha, G. Kambourakis, Improving Android malware detection through dimensionality reduction techniques, The 3rd International Conference on Machine Learning for Networking (MLN 2020), Nov, 2020, Paris, France, Springer LNCS,
 

Abstract
Mobile malware poses undoubtedly a major threat to the continuously increasing number of mobile users worldwide. While researchers have been trying vigorously to find optimal detection solutions, mobile malware is becoming more sophisticated and its writers are getting more and more skilled in hiding malicious code. In this paper, we examine the usefulness of two known dimensionality reduction transformations namely, Principal Component Analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) in malware detection. Starting from a large set of base prominent classifiers, we study how they can be combined to build an accurate ensemble. We propose a simple ensemble aggregated base model of similar feature type as well as a complex ensemble that can use multiple and possibly heterogeneous base models. The experimental results in contemporary Androzoo benchmark corpora verify the suitability of ensembles for this task and clearly demonstrate the effectiveness of our method.

N. Potha, E. Stamatatos, Dynamic Ensemble Selection for Author Verification, 41st European Conference on Information Retrieval (ECIR), pp. 102-115, Apr, 2019, Germany, Springer, http://dx.doi.org/10.1007/978-3-030...
 

Abstract
Author verification is a fundamental task in authorship analysis and associated with significant applications in humanities, cyber-security, and social media analytics. In some of the relevant studies, there is evidence that heterogeneous ensembles can provide very reliable solutions, better than any individual verification model. However, there is no systematic study of examining the application of ensemble methods in this task. In this paper, we start from a large set of base verification models covering the main paradigms in this area and study how they can be combined to build an accurate ensemble. We propose a simple stacking ensemble as well as a dynamic ensemble selection approach that can use the most reliable base models for each verification case separately. The experimental results in ten benchmark corpora covering multiple languages and genres verify the suitability of ensembles for this task and demonstrate the effectiveness of our method, in some cases improving the best reported results by more than 10%.

N. Potha, E. Stamatatos, Intrinsic Author Verification Using Topic Modeling, 10th Hellenic Conference on Artificial Intelligence (SETN), Jul, 2018, Patras, Greece, ACM, https://doi.org/10.1145/3200947.320...
 

Abstract
Author verification is a fundamental task in authorship analysis and associated with important applications in humanities and forensics. In this paper, we propose the use of an intrinsic profile-based verification method that is based on latent semantic indexing (LSI). Our proposed approach is easy-to-follow and language independent. Based on experiments using benchmark corpora from the PAN shared task in author verification, we demonstrate that LSI is both more effective and more stable than latent Dirichlet allocation in this task. Moreover, LSI models are able to outperform existing approaches especially when multiple texts of known authorship are available per verification instance and all documents belong to the same thematic area and genre. We also study several feature types and similarity measures to be combined with the proposed topic models.

N. Potha, E. Stamatatos, An Improved Impostors Method for Authorship Verification, CLEAF, Jones, G.J.F., Lawless, S., Gonzalo, J., Kelly, L., Goeuriot, L., Mandl, Th., Cappellato, L., Ferro, N. , (eds), pp. 138-144, Sep, 2017, Dublin, Ireland, Springer, Cham, https://doi.org/10.1007/978-3-319-6...
 

Abstract
Authorship verification has gained a lot of attention during the last years mainly due to the focus of PAN@CLEF shared tasks. A verification method called Impostors, based on a set of external (impostor) documents and a random subspace ensemble, is one of the most successful approaches. Variations of this method gained top-performing positions in recent PAN evaluation campaigns. In this paper, we propose a modification of the Impostors method that focuses on both appropriate selection of impostor documents and enhanced comparison of impostor documents with the documents under investigation. Our approach achieves competitive performance on PAN corpora, outperforming previous versions of the Impostors method.

[5]
N. Potha, M. Maragoudakis, Time Series Forecasting in Cyberbullying Data, 16th international conference on Engineering Applications of Neural Networks, EANN 2015, (eds), Dec, 2015, Rodos, Greece
N. Potha, M. Maragoudakis, Cyberbullying Detection using Time Series Modeling, IEEE ICDM 2014 - SENTIRE: 4th edition of Sentiment Elicitation from Natural Text for Information Retrieval and Extraction, (to_appear), Dec, 2014
 

Abstract
Cyberbullying is a new phenomenon resulting from the advance of new communication technologies including the Internet, cell phones and Personal Digital Assistants. It is a challenging bullying problem occurring in a new territory. Online bullying can be particularly damaging and upsetting because it's usually anonymous or hard to trace. In this paper, the proposed method is utilizing a dataset of real world conversations (i.e. pairs of questions and answers between cyber predator and the victim), in which each predator question is manually annotated in terms of severity using a numeric label. We approach the issue as a sequential data modelling approach, in which the predator’s questions are formulated using a Singular Value Decomposition representation. The motivation of this procedure is to study the accuracy of predicting the level of cyberbullying attack using classification methods and also to examine potential patterns between the lingustic style of each predator. More specifically, unlike previous approaches that consider a fixed window of a cyber-predator’s questions within a dialogue, we exploit the whole question set and model it as a signal, whose magnitude depends on the degree of bullying content. Using feature weighting and dimensionality reduction techniques, each signal is straightforwardly parsed by a neural network that forecasts the level of insult within a question given a window between two and three previous questions. Throughout the time series modeling experiments, an interesting discovery was made. By applying SVD on the time series data and taking into account the second dimension (since the first is usually modeling trivial dependencies between instances and attributes) we observed that its plot was very similar to the plot of the class attribute. By applying a Dynamic Time Warping algorithm, the similarity of the aforementioned signals was proved to exist, providing an immediate indicator for the severity of cyberbullying within a given dialogue.

[7]
N. Potha, E. Stamatatos, A Profile-based Method for Authorship Verification, 8th Hellenic Conference on Artificial Intelligence (SETN), pp. 313-326, Dec, 2014, Springer, http://dx.doi.org/10.1007/978-3-319...

Βιβλία


Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or mass reproduced without the explicit permission of the copyright holder.


Κεφάλαια σε Βιβλία


Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or mass reproduced without the explicit permission of the copyright holder.


Επιμέλεια Πρακτικών Διεθνών Συνεδρίων


Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or mass reproduced without the explicit permission of the copyright holder.