Konstantinos Tserpes

Jianning Li, Zongwei Zhou, Jiancheng Yang et al.

Prior to the deep learning era, shape was commonly used to describe the objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from numerous shape-related publications in premier vision conferences as well as the growing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models). For the medical domain, we present a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instrument, called MedShapeNet, created to facilitate the translation of data-driven vision algorithms to medical applications and to adapt SOTA vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. As of today, MedShapeNet includes 23 dataset with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface (API) and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing. Exemplary, we present use cases in the fields of classification of brain tumors, facial and skull reconstructions, multi-class anatomy completion, education, and 3D printing. In future, we will extend the data and improve the interfaces. The project pages are: https://medshapenet.ikim.nrw/ and https://github.com/Jianningli/medshapenet-feedback

Theodoros Theodoropoulos, John Violos, Stylianos Tsanakas et al.

The proliferation of demanding applications and edge computing establishes the need for an efficient management of the underlying computing infrastructures, urging the providers to rethink their operational methods. In this paper, we propose an Intelligent Proactive Fault Tolerance (IPFT) method that leverages the edge resource usage predictions through Recurrent Neural Networks (RNN). More specifically, we focus on the process-faults, which are related with the inability of the infrastructure to provide Quality of Service (QoS) in acceptable ranges due to the lack of processing power. In order to tackle this challenge we propose a composite deep learning architecture that predicts the resource usage metrics of the edge nodes and triggers proactive node replications and task migration. Taking also into consideration that the edge computing infrastructure is also highly dynamic and heterogeneous, we propose an innovative Hybrid Bayesian Evolution Strategy (HBES) algorithm for automated adaptation of the resource usage models. The proposed resource usage prediction mechanism has been experimentally evaluated and compared with other state of the art methods with significant improvements in terms of Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Additionally, the IPFT mechanism that leverages the resource usage predictions has been evaluated in an extensive simulation in CloudSim Plus and the results show significant improvement compared to the reactive fault tolerance method in terms of reliability and maintainability.

Panagiotis Rizomiliotis, Christos Diou, Aikaterini Triakosia et al.

Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based on a powerful cryptographic tools, like Homomorphic Encryption (HE) and/or multi-party computation (MPC). Even though the implementation of oblivious inference systems schemes has impressively improved the last decade, there are still significant limitations on the ML models that they can practically implement. Especially when both the ML model and the input data's confidentiality must be protected. In this paper, we introduce the notion of partially oblivious inference. We empirically show that for neural network models, like CNNs, some information leakage can be acceptable. We therefore propose a novel trade-off between security and efficiency. In our research, we investigate the impact on security and inference runtime performance from the CNN model's weights partial leakage. We experimentally demonstrate that in a CIFAR-10 network we can leak up to $80\%$ of the model's weights with practically no security impact, while the necessary HE-mutliplications are performed four times faster.

Ioannis Kontopoulos, Antonios Makris, Konstantinos Tserpes et al.

Due to the advent of new mobile devices and tracking sensors in recent years, huge amounts of data are being produced every day. Therefore, novel methodologies need to emerge that dive through this vast sea of information and generate insights and meaningful information. To this end, researchers have developed several trajectory classification algorithms over the years that are able to annotate tracking data. Similarly, in this research, a novel methodology is presented that exploits image representations of trajectories, called TraClets, in order to classify trajectories in an intuitive humans way, through computer vision techniques. Several real-world datasets are used to evaluate the proposed approach and compare its classification performance to other state-of-the-art trajectory classification algorithms. Experimental results demonstrate that TraClets achieves a classification performance that is comparable to, or in most cases, better than the state-of-the-art, acting as a universal, high-accuracy approach for trajectory classification.

Grigorios Papanikolaou, Ioannis Kontopoulos, Konstantinos Tserpes

Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant challenge. Therefore, smart and adaptive inference strategies that dynamically balance computational cost or latency with predictive accuracy are critical in edge computing scenarios. In this work, we build on Adaptive Deep Neural Networks (ADNNs) that employ the Multi-Armed Bandit (MAB) framework. Current literature leverages the first version of the Upper Confidence Bound (UCB1) strategy to dynamically select the optimal confidence threshold, enabling efficient early exits without sacrificing accuracy. However, we introduce four additional Upper Confidence Bound strategies in ADNNs, namely UCB-V, UCB-Tuned, UCB-Bayes, and UCB-BwK, and perform, for the first time, a comparative study of these strategies with respect to trade-offs between accuracy, energy consumption, and latency. The proposed UCB strategies are employed on the ResNet and MobileViT neural networks, and are evaluated on the benchmark datasets of CIFAR-10, CIFAR-10.1, and CIFAR-100. Experimental results demonstrate that all strategies achieve sub-linear cumulative regret, with UCB-Bayes converging the fastest, followed by UCB-Tuned and UCB-V. Finally, UCB-V and UCB-Tuned dominate the Pareto Frontiers of accuracy-latency and accuracy-energy trade-offs.

Ioannis Kontopoulos, Antonios Makris, Konstantinos Tserpes et al.

In recent years, the increased urbanization and industrialization has led to a rising water demand and resources, thus increasing the gap between demand and supply. Proper water distribution and forecasting of water consumption are key factors in mitigating the imbalance of supply and demand by improving operations, planning and management of water resources. To this end, in this paper, several well-known forecasting algorithms are evaluated over time series, water consumption data from Greece, a country with diverse socio-economic and urbanization issues. The forecasting algorithms are evaluated on a real-world dataset provided by the Water Supply and Sewerage Company of Greece revealing key insights about each algorithm and its use.

Stelio Bompai, Ioannis Kontopoulos, Giannis Spiliopoulos et al.

This paper addresses the problem of reconstructing missing or dropped frames in top-down drone video of autonomous surface vehicles performing structured maritime manoeuvres. We propose a pipeline that converts raw GPS telemetry and a single reference frame into a trajectory-guided video sequence using a pre-trained image-to-video diffusion model, requiring no domain-specific fine-tuning. GPS coordinates from onboard telemetry logs are projected into image space via an equirectangular mapping, producing per-vessel motion cues that condition the SG-I2V diffusion model. The generated frames are evaluated against ground-truth video using perceptual, temporal and trajectory-based metrics, and benchmarked against optical flow extrapolation and RIFE interpolation baselines. SG-I2V produces the most naturally appearing frames among all methods (BRISQUE 25.52, closest to ground-truth 23.64), the most realistic motion magnitude (temporal smoothness 1.14 vs. ground truth 1.42), and the strongest GPS trajectory adherence (9.31px vs. 28.70px for ground-truth, the latter reflecting approximate temporal alignment between footage and GPS logs rather than generation error), demonstrating that trajectory-guided diffusion synthesis is a viable approach to maritime video reconstruction under challenging low-texture, small-object conditions.

Stavros Bouras, Ioannis Kontopoulos, Chiara Pugliese et al.

Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generative Adversarial Networks, Variational Autoencoders, and Diffusion Models have been developed to generate realistic synthetic trajectory data by capturing underlying spatiotemporal distributions and mobility patterns. Although these models are often assumed to preserve privacy due to their generative nature, this assumption does not necessarily hold. In this work, we investigate the intersection of generative trajectory modeling and privacy evaluation. By identifying applicable empirical methods for assessing privacy preservation in trajectory generation tasks, we demonstrate a significant gap in the evaluation of privacy for generative trajectory models. Motivated by this gap, we implement Membership Inference Attacks against representative models, demonstrating the feasibility of using such empirical privacy evaluation methods and showing that their generative nature does not eliminate privacy risks.

Stavros Bouras, Ioannis Korontanis, Antonios Makris et al.

AI models are increasingly deployed in cloud-native environments to support scalable and automated services. However, while platforms such as Kubernetes provide strong infrastructure orchestration, security mechanisms specifically designed to protect deployed AI models remain limited. This paper presents security measures for AI models deployed in Kubernetes clusters. The proposed architecture integrates Kubeflow-based MLOps to automatically detect adversarial attacks during the inference phase and trigger defense mechanisms that preserve the model's accuracy and reliability. Specifically, a Fast Gradient Sign Method (FGSM) attack is applied at inference time, and a Projected Gradient Descent (PGD)-based adversarial training defense is automatically deployed when a degradation in accuracy is detected. The experimental results indicate that the deployed defense robustifies the model, significantly recovering accuracy relative to the degradation caused by the attack.

Grigorios Papanikolaou, Ioannis Kontopoulos, Giannis Spiliopoulos et al.

The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving efficient real-time perception. In such systems, object detection and trajectory perception of nearby vessels are tightly coupled, particularly in dynamic environments such as maritime navigation. However, the efficiency of object detection models during inference remains an often-overlooked aspect. To this end, we build upon an existing object detection framework by incorporating GPS trajectory data into the inference process to enable input-adaptive computation. Specifically, we introduce an early-exit mechanism in a YOLOv8-based detector that incorporates motion cues - such as inter-vessel distances. Frames of vessels that are separated by short distances, converging with high speed, are processed using the full model, while only a subset of the network's architecture is activated otherwise. The difficulty degree (or scene complexity) of a frame or set of frames per second is evaluated by leveraging inter-object distance and the rate at which the distance between them decreases. Experimental results demonstrate that this strategy maintains satisfactory detection performance while significantly reducing inference time and computational cost, thus enabling a flexible trade-off between accuracy and efficiency compared to full-model inference.

Antonios Makris, Christos Dousis, Emmanouil Kritharakis et al.

Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates at the server, which directly affects learning performance, robustness, and system behavior. This work presents a comprehensive experimental comparison of widely used federated aggregation strategies under both homogeneous and heterogeneous data distributions. Using benchmark image classification datasets, we analyze how different aggregation mechanisms respond to varying degrees of data heterogeneity, examining their impact on centralized accuracy and loss, and system-level efficiency metrics, including aggregation, training, and communication time. The results demonstrate that aggregation strategies exhibit distinct trade-offs across datasets and data distributions, with their effectiveness varying according to dataset characteristics and operating conditions.

Emmanouil Kritharakis, Antonios Makris, Dusan Jakovetic et al.

Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device. In this work, we address FL settings where clients may behave adversarially, exhibiting Byzantine attacks, while the central server is trusted and equipped with a reference dataset. We propose FedGreed, a resilient aggregation strategy for federated learning that does not require any assumptions about the fraction of adversarial participants. FedGreed orders clients' local model updates based on their loss metrics evaluated against a trusted dataset on the server and greedily selects a subset of clients whose models exhibit the minimal evaluation loss. Unlike many existing approaches, our method is designed to operate reliably under heterogeneous (non-IID) data distributions, which are prevalent in real-world deployments. FedGreed exhibits convergence guarantees and bounded optimality gaps under strong adversarial behavior. Experimental evaluations on MNIST, FMNIST, and CIFAR-10 demonstrate that our method significantly outperforms standard and robust federated learning baselines, such as Mean, Trimmed Mean, Median, Krum, and Multi-Krum, in the majority of adversarial scenarios considered, including label flipping and Gaussian noise injection attacks. All experiments were conducted using the Flower federated learning framework.

Emmanouil Kritharakis, Dusan Jakovetic, Antonios Makris et al.

Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted (honest) and has a trustworthy side dataset. This may correspond to, e.g., cases where the server possesses trusted data prior to federation, or to the presence of a trusted client that temporarily assumes the server role. Our approach requires only two honest participants, i.e., the server and one client, to function effectively, without prior knowledge of the number of malicious clients. Theoretical analysis demonstrates bounded optimality gaps even under strong Byzantine attacks. Experimental results show that our algorithm significantly outperforms standard and robust FL baselines such as Mean, Trimmed Mean, Median, Krum, and Multi-Krum under various attack strategies including label flipping, sign flipping, and Gaussian noise addition across MNIST, FMNIST, and CIFAR-10 benchmarks using the Flower framework.

Theodoros Theodoropoulos, Angelos-Christos Maroudis, Antonios Makris et al.

Regional traffic forecasting is a critical challenge in urban mobility, with applications to various fields such as the Internet of Everything. In recent years, spatio-temporal graph neural networks have achieved state-of-the-art results in the context of numerous traffic forecasting challenges. This work aims at expanding upon the conventional spatio-temporal graph neural network architectures in a manner that may facilitate the inclusion of information regarding the examined regions, as well as the populations that traverse them, in order to establish a more efficient prediction model. The end-product of this scientific endeavour is a novel spatio-temporal graph neural network architecture that is referred to as WEST (WEighted STacked) GCN-LSTM. Furthermore, the inclusion of the aforementioned information is conducted via the use of two novel dedicated algorithms that are referred to as the Shared Borders Policy and the Adjustable Hops Policy. Through information fusion and distillation, the proposed solution manages to significantly outperform its competitors in the frame of an experimental evaluation that consists of 19 forecasting models, across several datasets. Finally, an additional ablation study determined that each of the components of the proposed solution contributes towards enhancing its overall performance.

Antonios Makris, Theodoros Theodoropoulos, Evangelos Psomakelis et al.

The shift from Cloud Computing to a Cloud-Edge continuum presents new opportunities and challenges for data-intensive and interactive applications. Edge computing has garnered a lot of attention from both industry and academia in recent years, emerging as a key enabler for meeting the increasingly strict demands of Next Generation applications. In Edge computing the computations are placed closer to the end-users, to facilitate low-latency and high-bandwidth applications and services. However, the distributed, dynamic, and heterogeneous nature of Edge computing, presents a significant challenge for service placement. A critical aspect of Edge computing involves managing the placement of applications within the network system to minimize each application's runtime, considering the resources available on system devices and the capabilities of the system's network. The placement of application images must be proactively planned to minimize image tranfer time, and meet the strict demands of the applications. In this regard, this paper proposes an approach for proactive image placement that combines Graph Neural Networks and actor-critic Reinforcement Learning, which is evaluated empirically and compared against various solutions. The findings indicate that although the proposed approach may result in longer execution times in certain scenarios, it consistently achieves superior outcomes in terms of application placement.

Valerio De Caro, Saira Bano, Achilles Machumilane et al.

This paper presents a proof-of-concept implementation of the AI-as-a-Service toolkit developed within the H2020 TEACHING project and designed to implement an autonomous driving personalization system according to the output of an automatic driver's stress recognition algorithm, both of them realizing a Cyber-Physical System of Systems. In addition, we implemented a data-gathering subsystem to collect data from different sensors, i.e., wearables and cameras, to automatize stress recognition. The system was attached for testing to a driving simulation software, CARLA, which allows testing the approach's feasibility with minimum cost and without putting at risk drivers and passengers. At the core of the relative subsystems, different learning algorithms were implemented using Deep Neural Networks, Recurrent Neural Networks, and Reinforcement Learning.

Davide Bacciu, Siranush Akarmazyan, Eric Armengaud et al.

This paper discusses the perspective of the H2020 TEACHING project on the next generation of autonomous applications running in a distributed and highly heterogeneous environment comprising both virtual and physical resources spanning the edge-cloud continuum. TEACHING puts forward a human-centred vision leveraging the physiological, emotional, and cognitive state of the users as a driver for the adaptation and optimization of the autonomous applications. It does so by building a distributed, embedded and federated learning system complemented by methods and tools to enforce its dependability, security and privacy preservation. The paper discusses the main concepts of the TEACHING approach and singles out the main AI-related research challenges associated with it. Further, we provide a discussion of the design choices for the TEACHING system to tackle the aforementioned challenges

Evangelos Psomakelis, Konstantinos Tserpes, Dimitris Zissisc et al.

Predicting the next position of movable objects has been a problem for at least the last three decades, referred to as trajectory prediction. In our days, the vast amounts of data being continuously produced add the big data dimension to the trajectory prediction problem, which we are trying to tackle by creating a λ-Architecture based analytics platform. This platform performs both batch and stream analytics tasks and then combines them to perform analytical tasks that cannot be performed by analyzing any of these layers by itself. The biggest benefit of this platform is its context agnostic trait, which allows us to use it for any use case, as long as a time-stamped geolocation stream is provided. The experimental results presented prove that each part of the λ-Architecture performs well at certain targets, making a combination of these parts a necessity in order to improve the overall accuracy and performance of the platform.

Angelos Valsamis, Konstantinos Tserpes, Dimitrios Zissis et al.

In this paper, we model the trajectory of sea vessels and provide a service that predicts in near-real time the position of any given vessel in 4', 10', 20' and 40' time intervals. We explore the necessary tradeoffs between accuracy, performance and resource utilization are explored given the large volume and update rates of input data. We start with building models based on well-established machine learning algorithms using static datasets and multi-scan training approaches and identify the best candidate to be used in implementing a single-pass predictive approach, under real-time constraints. The results are measured in terms of accuracy and performance and are compared against the baseline kinematic equations. Results show that it is possible to efficiently model the trajectory of multiple vessels using a single model, which is trained and evaluated using an adequately large, static dataset, thus achieving a significant gain in terms of resource usage while not compromising accuracy.

Evangelos Psomakelis, Fotis Aisopos, Antonios Litke et al.

In this paper we present a SOA (Service Oriented Architecture)-based platform, enabling the retrieval and analysis of big datasets stemming from social networking (SN) sites and Internet of Things (IoT) devices, collected by smart city applications and socially-aware data aggregation services. A large set of city applications in the areas of Participating Urbanism, Augmented Reality and Sound-Mapping throughout participating cities is being applied, resulting into produced sets of millions of user-generated events and online SN reports fed into the RADICAL platform. Moreover, we study the application of data analytics such as sentiment analysis to the combined IoT and SN data saved into an SQL database, further investigating algorithmic and configurations to minimize delays in dataset processing and results retrieval.

Magdalini Kardara, Vasilis Kalogirou, Athanasios Papaoikonomou et al.

Following the boost in popularity of online social networks, both enterprises and researchers looked for ways to access the social dynamics information and user generated content residing in these spaces. This endeavor, however, presented several challenges caused by the heterogeneity of data and the lack of a common way to access them. The SocIoS framework tries to address these challenges by providing tools that operate on top of multiple popular social networks allowing uniform access to their data. It provides a single access point for aggregating data and functionality from the networks, as well as a set of analytical tools for exploiting them. In this paper we present the SocIoS API, an abstraction layer on top of the social networks exposing operations that encapsulate the functionality of their APIs. Currently, the component provides support for seven social networks and is flexible enough to allow for the seamless addition of more.

Evangelos Psomakelis, Konstantinos Tserpes, Dimosthenis Anagnostopoulos et al.

This work extends the set of works which deal with the popular problem of sentiment analysis in Twitter. It investigates the most popular document ("tweet") representation methods which feed sentiment evaluation mechanisms. In particular, we study the bag-of-words, n-grams and n-gram graphs approaches and for each of them we evaluate the performance of a lexicon-based and 7 learning-based classification algorithms (namely SVM, Naïve Bayesian Networks, Logistic Regression, Multilayer Perceptrons, Best-First Trees, Functional Trees and C4.5) as well as their combinations, using a set of 4451 manually annotated tweets. The results demonstrate the superiority of learning-based methods and in particular of n-gram graphs approaches for predicting the sentiment of tweets. They also show that the combinatory approach has impressive effects on n-grams, raising the confidence up to 83.15% on the 5-Grams, using majority vote and a balanced dataset (equal number of positive, negative and neutral tweets for training). In the n-gram graph cases the improvement was small to none, reaching 94.52% on the 4-gram graphs, using Orthodromic distance and a threshold of 0.001.