A5023985839- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Software-Defined Networks and 5G
- Energy Efficient Wireless Sensor Networks
- Mobile Ad Hoc Networks
- Advanced Malware Detection Techniques
- Privacy-Preserving Technologies in Data
- Smart Grid Security and Resilience
- Green IT and Sustainability
- Network Security and Intrusion Detection
- Advanced Data Storage Technologies
- European Criminal Justice and Data Protection
- Distributed and Parallel Computing Systems
- Context-Aware Activity Recognition Systems
- Anomaly Detection Techniques and Applications
- Parallel Computing and Optimization Techniques
- Adversarial Robustness in Machine Learning
- Cryptography and Data Security
- Smart Grid Energy Management
- Internet Traffic Analysis and Secure E-voting
- Power System Reliability and Maintenance
- Big Data and Business Intelligence
- Patient Safety and Medication Errors
- Digital and Cyber Forensics
- Smart Agriculture and AI
Synelixis (Greece)
2018-2024
Exelixis (United States)
2021
SingularLogic (Greece)
2015-2020
Technological Educational Institute of Thessaly
2014
National Technical University of Athens
2012
The diversity of applications that current and emerging Wireless Sensor Networks (WSNs) are called to support imposes different requirements on the underlying network with respect delay loss, while at same time WSN its own intricacies. satisfaction these highly depends metric upon which forwarding routes decided. In this view, IETF ROLL group has proposed RPL routing protocol, can flexibly work various metrics, as long they hold specific properties. system implementer/user is free decide...
Network intrusion detection is a key pillar towards the sustainability and normal operation of information systems. Complex threat patterns malicious actors are able to cause severe damages cyber-systems. In this work, we propose novel Deep Learning formulations for detecting threats alerts on network logs that were acquired by pfSense, an open-source software acts as firewall FreeBSD operating system. pfSense integrates several powerful security services such firewall, URL filtering,...
The energy sector represents undoubtedly one of the most significant "test cases" for 5G enabling technologies, due to need addressing a huge range very diverse requirements deal with across variety applications (stringent capacity smart metering/AMI versus latency supervisory control and fault localization).However, effectively support utilities along their transition towards more decentralized renewable-oriented systems, several open issues still remain as networks management automation,...
Federated learning (FL) is an emerging machine technique where models are trained in a decentralized manner. The main advantage of this approach the data privacy it provides because not processed centralized device. Moreover, local client aggregated on server, resulting global model that has accumulated knowledge from all different clients. This approach, however, vulnerable to attacks clients can be malicious or actors may interfere within network. In first case, these types refer poisoning...
Wireless Sensor Networks (WSNs) often need to operate under strict requirements on energy consumption and be capable of self-adapting the presence non-trusted nodes which do not fully cooperate in packet forwarding operation. In such an environment, mechanism employed for calculation routing paths minimum cost terms number transmissions executed reliable communication between data source sink is essential prevent unnecessary nodes' depletion help prolong network's lifetime. this paper, we...
Nowadays, IoT networks and devices exist in our everyday life, capturing carrying unlimited data. However, increasing penetration of connected systems implies rising threats for cybersecurity with suffering from network attacks. Artificial Intelligence (AI) Machine Learning take advantage huge volumes logs to enhance their IoT. these data are often desired remain private. Federated (FL) provides a potential solution which enables collaborative training attack detection model among set...
Intrusion detection plays a critical role in cyber-security domain since malicious attacks cause irreparable damages to cyber-systems. In this work, we propose the I2SP prototype, which is novel Information Sharing Platform, able gather, pre-process, model, and distribute network-traffic information. Within prototype build several challenging deep feature learning models for intrusion detection. The learnt representations will be utilized classifying each new network measurement into its...
Artificial Intelligence of Things (AIoT) is one the next big concepts to support societal changes and economic growth, being fastest growing ICT segments. A specific challenge leverage existing technology strengths develop solutions that sustain European industry values. The ongoing ΝΕΜΟ ("Next Generation Meta-Operating System") EU-funded project intends establish itself as "game changer" AIoT-Edge-Cloud continuum by introducing an open source, modular cybersecure meta-operating system,...
Autonomous fault detection plays a major role in the Critical Energy Infrastructure (CEI) domain, since sensor faults cause irreparable damage and lead to incorrect results on condition monitoring of Cyber-Physical (CP) systems. This paper focuses challenging application wind turbine (WT) monitoring. Specifically, we propose two architectures based learning deep features, namely—Long Short Term Memory-Stacked Autoencoders (LSTM-SAE), Convolutional Neural Network (CNN-SAE), for...
This position paper presents a novel heterogeneous CPU-GPU multi-level cloud acceleration focusing on applications running embedded systems found low-power devices. A runtime system performs energy and performance estimations in order to automatically select local CPU-based GPU-based tasks that should be seamlessly executed more powerful remote devices or infrastructures. Moreover, it proposes, for the first time, secure unified model where almost any device infrastructure can operate as an...
This paper addresses the challenge of olive tree segmentation using drone imagery, which is crucial for precision agriculture applications. We tackle data scarcity issue by augmenting existing detection datasets. Additionally, lightweight model variations state-of-the-art models like YOLOv8n, RepViT-SAM, and EdgeSAM are combined into two proposed pipelines to meet computational constraints while maintaining accuracy. Our multifaceted approach successfully achieves an equilibrium among size,...
The energy sector has been, in recent years, the target of sophisticated cyberattacks. Although importance collaborative cyber-security consciousness, expressed as extensive cyber threat intelligence sharing, is undoubted, standardization means exchanging information efficiently and securely been inadequately addressed mostly by emergence Trusted Automated eXchange Indicator Information (TAXIITM) protocol which faces major deficiencies when it comes to data integrity assurance suitability...
Federated Learning is identified as a reliable technique for distributed training of ML models. Specifically, set dispersed nodes may collaborate through federation in producing jointly trained model without disclosing their data to each other. Each node performs local and then shares its weights with server node, usually called Aggregator federated learning, it aggregates the sends them back clients another round training. Despite protection security that FL provides client, there are still...
In this paper, we address the management of Data Centers (DCs) by considering their optimal integration with electrical, thermal, and IT (Information Technology) networks helping them to meet sustainability objectives gain primary energy savings. Innovative scenarios are defined for exploiting DCs workload flexibility as a commodity Information Communication Technologies (ICT) proposed used enablers scenarios’ implementation. The technology were evaluated in context two operational DCs:...
An innovative approach for increasing the energy efficiency of Data Centers is discussed. This views as active load resources, integrated in context smart city and operated a coordinated manner. can thus contribute to establishing sustainable, local, management ecosystems on level, while enabling optimized operation involved grids. To that end, development local marketplaces will allow trading surplus energy, both electricity thermal, provide balancing flexibility ancillary services....
The increasing demand for highly sophisticated cloud services and the consequent worldwide increase in number of data centers (DC), make need energy efficient operation DCs more actual than ever. Additionally, context smart city grid integration, flexible can play a key role toward acting as grid-stabilization factors. In this paper, review available techniques energy-efficient DC is performed. give rise to four axes flexibility within federated network. Next, applicability flexible,...
Current partially or even no automated in-hospital processes often allow unacceptable errors to occur, the effects of which may span from simple injury mortality. Recent advances in Internet Things, smart tags and cloud technologies decisively alter this fact minimize such "never events". In paper, MATISSE is presented as a hospital ecosystem, aiming decrease events" value chain. Real-time drugs/pills lifetime/aptness verification medication administration, patients' identification...