2021
|
1. | Spyridis, Yannis; Lagkas, Thomas; Sarigiannidis, Panagiotis; Argyriou, Vasileios; Sarigiannidis, Antonios; Eleftherakis, George; Zhang, Jie Towards 6G IoT: Tracing mobile sensor nodes with deep learning clustering in UAV networks (Journal Article) In: Sensors, vol. 21, no. 11, pp. 3936, 2021. @article{spyridis2021towards,
title = {Towards 6G IoT: Tracing mobile sensor nodes with deep learning clustering in UAV networks},
author = {Yannis Spyridis and Thomas Lagkas and Panagiotis Sarigiannidis and Vasileios Argyriou and Antonios Sarigiannidis and George Eleftherakis and Jie Zhang},
url = {https://www.mdpi.com/1424-8220/21/11/3936},
doi = {10.3390/s21113936},
year = {2021},
date = {2021-06-07},
urldate = {2021-01-01},
journal = {Sensors},
volume = {21},
number = {11},
pages = {3936},
publisher = {MDPI},
abstract = {Unmanned aerial vehicles (UAVs) in the role of flying anchor nodes have been proposed to assist the localisation of terrestrial Internet of Things (IoT) sensors and provide relay services in the context of the upcoming 6G networks. This paper considered the objective of tracing a mobile IoT device of unknown location, using a group of UAVs that were equipped with received signal strength indicator (RSSI) sensors. The UAVs employed measurements of the target’s radio frequency (RF) signal power to approach the target as quickly as possible. A deep learning model performed clustering in the UAV network at regular intervals, based on a graph convolutional network (GCN) architecture, which utilised information about the RSSI and the UAV positions. The number of clusters was determined dynamically at each instant using a heuristic method, and the partitions were determined by optimising an RSSI loss function. The proposed algorithm retained the clusters that approached the RF source more effectively, removing the rest of the UAVs, which returned to the base. Simulation experiments demonstrated the improvement of this method compared to a previous deterministic approach, in terms of the time required to reach the target and the total distance covered by the UAVs.},
keywords = {6G, Deep Learning, Internet of Things (IoT), Sensors, Unmanned aerial vehicles},
pubstate = {published},
tppubtype = {article}
}
Unmanned aerial vehicles (UAVs) in the role of flying anchor nodes have been proposed to assist the localisation of terrestrial Internet of Things (IoT) sensors and provide relay services in the context of the upcoming 6G networks. This paper considered the objective of tracing a mobile IoT device of unknown location, using a group of UAVs that were equipped with received signal strength indicator (RSSI) sensors. The UAVs employed measurements of the target’s radio frequency (RF) signal power to approach the target as quickly as possible. A deep learning model performed clustering in the UAV network at regular intervals, based on a graph convolutional network (GCN) architecture, which utilised information about the RSSI and the UAV positions. The number of clusters was determined dynamically at each instant using a heuristic method, and the partitions were determined by optimising an RSSI loss function. The proposed algorithm retained the clusters that approached the RF source more effectively, removing the rest of the UAVs, which returned to the base. Simulation experiments demonstrated the improvement of this method compared to a previous deterministic approach, in terms of the time required to reach the target and the total distance covered by the UAVs. |
2. | Grammatikis, Panagiotis Radoglou; Sarigiannidis, Panagiotis; Iturbe, Eider; Rios, Erkuden; Martinez, Saturnino; Sarigiannidis, Antonios; Efstathopoulos, Georgios; Spyridis, Yannis; Sesis, Achilleas; Vakakis, Nikolaos; Tzovaras, Dimitrios; Kafetzakis, Emmanouil; Giannoulakis, Ioannis; Tzifas, Michalis; Giannakoulias, Alkiviadis; Angelopoulos, Michail; Ramos, Francisco SPEAR SIEM: A Security Information and Event Management system for the Smart Grid (Journal Article) In: Computer Networks, 2021. @article{article,
title = {SPEAR SIEM: A Security Information and Event Management system for the Smart Grid},
author = {Panagiotis Radoglou Grammatikis and Panagiotis Sarigiannidis and Eider Iturbe and Erkuden Rios and Saturnino Martinez and Antonios Sarigiannidis and Georgios Efstathopoulos and Yannis Spyridis and Achilleas Sesis and Nikolaos Vakakis and Dimitrios Tzovaras and Emmanouil Kafetzakis and Ioannis Giannoulakis and Michalis Tzifas and Alkiviadis Giannakoulias and Michail Angelopoulos and Francisco Ramos},
url = {https://www.researchgate.net/publication/350287201_SPEAR_SIEM_A_Security_Information_and_Event_Management_system_for_the_Smart_Grid},
doi = {10.1016/j.comnet.2021.108008},
year = {2021},
date = {2021-01-01},
journal = {Computer Networks},
abstract = {The technological leap of smart technologies has brought the conventional electrical grid in a new digital era called Smart Grid (SG), providing multiple benefits, such as two-way communication, pervasive control and self-healing. However, this new reality generates significant cybersecurity risks due to the heterogeneous and insecure nature of SG. In particular, SG relies on legacy communication protocols that have not been implemented having cybersecurity in mind. Moreover, the advent of the Internet of Things (IoT) creates severe cybersecurity challenges. The Security Information and Event Management (SIEM) systems constitute an emerging technology in the cybersecurity area, having the capability to detect, normalise and correlate a vast amount of security events. They can orchestrate the entire security of a smart ecosystem, such as SG. Nevertheless, the current SIEM systems do not take into account the unique SG peculiarities and characteristics like the legacy communication protocols. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) SIEM, which focuses on SG. The main contribution of our work is the design and implementation of a SIEM system capable of detecting, normalising and correlating cyberattacks and anomalies against a plethora of SG application-layer protocols. It is noteworthy that the detection performance of the SPEAR SIEM is demonstrated with real data originating from four real SG use case (a) hydropower plant, (b) substation, (c) power plant and (d) smart home.},
keywords = {Anomaly Detection, Auto-encoder, Cybersecurity, Deep Learning, Generative Adversarial Network, Machine Learning, Modbus, Smart Grid},
pubstate = {published},
tppubtype = {article}
}
The technological leap of smart technologies has brought the conventional electrical grid in a new digital era called Smart Grid (SG), providing multiple benefits, such as two-way communication, pervasive control and self-healing. However, this new reality generates significant cybersecurity risks due to the heterogeneous and insecure nature of SG. In particular, SG relies on legacy communication protocols that have not been implemented having cybersecurity in mind. Moreover, the advent of the Internet of Things (IoT) creates severe cybersecurity challenges. The Security Information and Event Management (SIEM) systems constitute an emerging technology in the cybersecurity area, having the capability to detect, normalise and correlate a vast amount of security events. They can orchestrate the entire security of a smart ecosystem, such as SG. Nevertheless, the current SIEM systems do not take into account the unique SG peculiarities and characteristics like the legacy communication protocols. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) SIEM, which focuses on SG. The main contribution of our work is the design and implementation of a SIEM system capable of detecting, normalising and correlating cyberattacks and anomalies against a plethora of SG application-layer protocols. It is noteworthy that the detection performance of the SPEAR SIEM is demonstrated with real data originating from four real SG use case (a) hydropower plant, (b) substation, (c) power plant and (d) smart home. |
3. | Siniosoglou, Ilias; Argyriou, Vasileios; Lagkas, Thomas; Tsiakalos, Apostolos; Sarigiannidis, Antonios; Sarigiannidis, Panagiotis Covert Distributed Training of Deep Federated Industrial Honeypots (Inproceedings) In: 2021 IEEE Globecom Workshops (GC Wkshps), pp. 1–6, IEEE 2021. @inproceedings{siniosoglou2021covert,
title = {Covert Distributed Training of Deep Federated Industrial Honeypots},
author = {Ilias Siniosoglou and Vasileios Argyriou and Thomas Lagkas and Apostolos Tsiakalos and Antonios Sarigiannidis and Panagiotis Sarigiannidis},
url = {https://ieeexplore.ieee.org/abstract/document/9682162},
doi = {10.1109/GCWkshps52748.2021.9682162},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 IEEE Globecom Workshops (GC Wkshps)},
pages = {1--6},
organization = {IEEE},
abstract = {Since the introduction of automation technologies in the Industrial field and its subsequent scaling to horizontal and vertical extents, the need for interconnected industrial systems, supporting smart interoperability is ever higher. Due to this scaling, new and critical vulnerabilities have been created, notably in legacy systems, leaving Industrial infrastructures prone to cyber attacks, that can some times have catastrophic results. To tackle the need for extended security measures, this paper presents a Federated Industrial Honeypot that takes advantage of decentralized private Deep Training to produce models that accumulate and simulate real industrial devices. To enhance their camouflage, SCENT, a new custom and covert protocol is proposed, to fully immerse the Federated Honeypot to its industrial role, that handles the communication between the server and honeypot during the training, to hide any clues of operation of the honeypot other that its supposed objective to the eye of the attacker.},
keywords = {Data Generation, Deep Learning, Honeypots, Industrial Control System, SCADA},
pubstate = {published},
tppubtype = {inproceedings}
}
Since the introduction of automation technologies in the Industrial field and its subsequent scaling to horizontal and vertical extents, the need for interconnected industrial systems, supporting smart interoperability is ever higher. Due to this scaling, new and critical vulnerabilities have been created, notably in legacy systems, leaving Industrial infrastructures prone to cyber attacks, that can some times have catastrophic results. To tackle the need for extended security measures, this paper presents a Federated Industrial Honeypot that takes advantage of decentralized private Deep Training to produce models that accumulate and simulate real industrial devices. To enhance their camouflage, SCENT, a new custom and covert protocol is proposed, to fully immerse the Federated Honeypot to its industrial role, that handles the communication between the server and honeypot during the training, to hide any clues of operation of the honeypot other that its supposed objective to the eye of the attacker. |
4. | Sun, Zhonglin; Spyridis, Yannis; Sessis, Achilleas; Efstathopoulos, Georgios; Grigoriou, Elisavet; Lagkas, Thomas; Sarigiannidis, Panagiotis Intentional Islanding of Power Systems Through Self-Embedding Learning (Inproceedings) In: 2021 IEEE Globecom Workshops (GC Wkshps), pp. 1–6, IEEE 2021. @inproceedings{sun2021intentional,
title = {Intentional Islanding of Power Systems Through Self-Embedding Learning},
author = {Zhonglin Sun and Yannis Spyridis and Achilleas Sessis and Georgios Efstathopoulos and Elisavet Grigoriou and Thomas Lagkas and Panagiotis Sarigiannidis},
url = {https://ieeexplore.ieee.org/abstract/document/9682069},
doi = {10.1109/GCWkshps52748.2021.9682069},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 IEEE Globecom Workshops (GC Wkshps)},
pages = {1--6},
organization = {IEEE},
abstract = {Intentional islanding is a procedure to divide the electrical grid into several parts to guarantee the stability of a system in the case of failure. This study provides an unsupervised deep neural network to deal with the issue of intentional islanding. We propose to use a self-learning neural network to improve the generalisation performance of the islanding task. In addition, we use a merging technology to assign isolated buses to their neighbour's label. Experiments are carried out on several grid cases to illustrate the effect of our solution.},
keywords = {Deep Learning, Intentional islanding, Smart Grid},
pubstate = {published},
tppubtype = {inproceedings}
}
Intentional islanding is a procedure to divide the electrical grid into several parts to guarantee the stability of a system in the case of failure. This study provides an unsupervised deep neural network to deal with the issue of intentional islanding. We propose to use a self-learning neural network to improve the generalisation performance of the islanding task. In addition, we use a merging technology to assign isolated buses to their neighbour's label. Experiments are carried out on several grid cases to illustrate the effect of our solution. |