Christos Douligeris

Iakovos-Christos Zarkadis, Christos Douligeris

During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), has been introduced, to explain the decisions made by complex machine learning (ML) models in critical systems like UAV intrusion detection systems (UAVIDS). In this paper, we apply best-practices for data pre-processing and examine a wide range of tree-ensembles, deep neural networks, hybrid stacking models and the latest ensemble neural networks to detect intrusions in UAV, with stratified 10-fold cross validation. With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. Furthermore a distribution analysis follows, by visually comparing violin plots and the curves of kernel density estimations. With the Westfall-Young permutation test for multiple comparisons, the Bandwidth optimization of the KDEs and the selection of Jensen-Shannon Distance for the test, we discover the true causes of false predictions, observed in Wormhole and Blackhole attacks in UAVIDS-2025. The findings provide robust, reliable and explainable models for UAV intrusion detection, along with statistical insights, which capture and clarify the masked nature of the attacks, regarding the challenge of Density Support Intersection, between these attacks, in this dataset.

Iakovos-Christos Zarkadis, Christos Douligeris

Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.

Vasilis Papaspirou, Maria Papathanasaki, Leandros Maglaras et al.

Although sufficient authentication mechanisms were enhanced by the use of two or more factors that resulted in new multi factor authentication schemes, more sophisticated and targeted attacks have shown they are also vulnerable. This research work proposes a novel two factor authentication system that incorporates honeytokens into the two factor authentication process. The current implementation collaborates with Google authenticator. The novelty and simplicity of the presented approach aims at providing additional layers of security and protection into a system and thus making it more secure through a stronger and more efficient authentication mechanism.

Vassilis Papaspirou, Leandros Maglaras, Mohamed Amine Ferrag et al.

The majority of systems rely on user authentication on passwords, but passwords have so many weaknesses and widespread use that easily raise significant security concerns, regardless of their encrypted form. Users hold the same password for different accounts, administrators never check password files for flaws that might lead to a successful cracking, and the lack of a tight security policy regarding regular password replacement are a few problems that need to be addressed. The proposed research work aims at enhancing this security mechanism, prevent penetrations, password theft, and attempted break-ins towards securing computing systems. The selected solution approach is two-folded; it implements a two-factor authentication scheme to prevent unauthorized access, accompanied by Honeyword principles to detect corrupted or stolen tokens. Both can be integrated into any platform or web application with the use of QR codes and a mobile phone.

Dimitrios Kallergis, Zacharenia Garofalaki, Georgios Katsikogiannis et al.

The microservices architectural approach has important benefits regarding the agile applications' development and the delivery of complex solutions. However, to convey the information and share the data amongst services in a verifiable and stateless way, there is a need to enable appropriate access control methods and authorisations. In this paper, we study the use of policy-driven authorisations with independent fine-grained microservices in the case of a real-world machine-to-machine (M2M) scenario using a hybrid cloud-based infrastructure and Internet of Things (IoT) services. We also model the authentication flows which facilitate the message exchanges between the involved entities, and we propose a containerised authorisation and policy-driven architecture (CAPODAZ) using the microservices paradigm. The proposed architecture implements a policy-based management framework and integrates in an on-going work regarding a Cloud-IoT intelligent transportation service. For the in-depth quantitative evaluation, we treat multiple distributions of users' populations and assess the proposed architecture against other similar microservices. The numerical results based on the experimental data show that there exists significant performance preponderance in terms of latency, throughput and successful requests.

Zacharenia Garofalaki, Dimitrios Kallergis, Georgios Katsikogiannis et al.

Recent advancements in the field of smart machine-to-machine (M2M) communications impose the necessity to improve the service delivery by enforcing appropriate security rules. Due to the large number of connected devices, the criticality of the M2M applications, and the network stability weaknesses, we need to consider and analyse the security aspects and establish a flexible policy-aware architecture. This paper explores the relevant architectural challenges in this environment and proposes a Policy-Aware smart M2M Architecture (PAArc) based on ETSI M2M communications functional architecture. We explore the policy-based management aspects to improve the security of the M2M components and services and to mitigate the security concerns that arise by evaluating an Intelligent Transportation System use case. It is shown that the policy enforcement enables enhanced security management capabilities, increased agility, and better service levels in the field of smart M2M communications.

Michael Mpasios, Dimitrios Kallergis, Konstantinos Chimos et al.

Our entire society is becoming more and more dependent on technology and specifically on software. The integration of e-learning software systems into our day by day life especially in e-learning applications generates modifications upon the society and, at the same time, the society itself changes the process of software development. This circle of continuous determination engenders a highly dynamic environment. Lehman describes the software development environment as being characterized by a high, necessary and inevitable pressure for change. Changes are reflected in specific uncertainties which impact the success and performance of the software project development.

Dimitrios Kallergis, Konstantinos Chimos, Vizikidis Stefanos et al.

In this paper a new Web-based File Hosting Service with Object Oriented Logic in Cloud Computing called Pirus was developed. The service will be used by the academic community of the University of Piraeus giving users the ability to remotely store and access their personal files with no security compromises. It also offers the administrators the ability to manage users and roles. The objective was to deliver a fully operational service, using state-of-the-art programming techniques to enable scalability and future development of the existing functionality. The use of technologies such as .NET Framework, C# programming language, CSS and jQuery, MSSQL for database hosting and the support of Virtualization and Cloud Computing will contribute significantly in compatibility, code reuse, reliability and reduce of maintenance costs and resources. The service was installed and tested in a controlled environment to ascertain the required functionality and the offered reliability and safety with complete success. The technologies used and supported, allow future work in upgrading and extending the service. Changes and improvements, in hardware and software, in order to convert the service to a SaaS (Software as a Service) Cloud application is a logical step in order to efficiently offer the service to a wider community. Improved and added functionality offered by further development will leverage the user experience.