2026
Dimitrios Tyrovolas Thrassos K. Oikonomou, Sotiris A. Tegos
A Novel Detector under Generalized Hardware Impairments Proceedings Article Forthcoming
In: IEEE International Conference on Communications (ICC), Forthcoming.
@inproceedings{icc_detector_amyna,
title = {A Novel Detector under Generalized Hardware Impairments},
author = {Thrassos K. Oikonomou, Dimitrios Tyrovolas, Sotiris A. Tegos, Panagiotis D. Diamantoulakis, Panagiotis Sarigiannidis, George K. Karagiannidis},
doi = {ΣΥΜΠΛΗΡΩΣΕ_DOI_ΑΝ_ΥΠΑΡΧΕΙ},
year = {2026},
date = {2026-07-01},
urldate = {2026-07-01},
booktitle = {IEEE International Conference on Communications (ICC)},
abstract = {This paper presents, for the first time, a maximum-likelihood detection framework that jointly mitigates hardware impairments in both amplitude and phase. By modeling transceiver distortions as residual amplitude and phase noise (PN), we derive the approximate phase-and-amplitude distortion detector (PAD-D), which operates in the polar domain and effectively mitigates both distortion components through distortion-aware weighting.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
This paper presents, for the first time, a maximum-likelihood detection framework that jointly mitigates hardware impairments in both amplitude and phase. By modeling transceiver distortions as residual amplitude and phase noise (PN), we derive the approximate phase-and-amplitude distortion detector (PAD-D), which operates in the polar domain and effectively mitigates both distortion components through distortion-aware weighting.
P. S. Bouzinis N. A. Mitsiou, P. G. Sarigiannidis; Karagiannidis, G. K.
Heterogeneous Resource Allocation With Multi-Task Learning for Wireless Networks Journal Article
In: IEEE Transactions on Wireless Communications, vol. 25, pp. 7191–7205, 2026.
@article{mitsiou2026heterogeneous,
title = {Heterogeneous Resource Allocation With Multi-Task Learning for Wireless Networks},
author = {N. A. Mitsiou, P. S. Bouzinis, P. G. Sarigiannidis and G. K. Karagiannidis},
doi = {10.1109/TWC.2025.3630058},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {IEEE Transactions on Wireless Communications},
volume = {25},
pages = {7191–7205},
abstract = {Given the nature of wireless networks, which involves multiple and diverse objectives that can have conflicting requirements and constraints, we propose a multi-task learning (MTL) framework to enable a single DNN to jointly solve a range of diverse optimization problems. In this framework, optimization problems with varying dimensionality values, objectives, and constraints are treated as distinct tasks. To jointly address these tasks, we propose a conditional computation-based MTL approach with routing.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Given the nature of wireless networks, which involves multiple and diverse objectives that can have conflicting requirements and constraints, we propose a multi-task learning (MTL) framework to enable a single DNN to jointly solve a range of diverse optimization problems. In this framework, optimization problems with varying dimensionality values, objectives, and constraints are treated as distinct tasks. To jointly address these tasks, we propose a conditional computation-based MTL approach with routing.
2025
Panagiotis Radoglou-Grammatikis Dimitrios-Christos Asimopoulos, Vasileios Argyriou
Hybrid-FGPG: A Novel Fusion of Gradient and Geometric Transformations for Adversarial Vulnerability Evaluation Proceedings Article
In: IEEE Global Communications Conference (GLOBECOM) Workshops, Taipei, Taiwan, 2025, (Presented at WS-18: The Third Workshop on SIGNIS: Softwarized Next Generation Networks for IoT Services, December 8–12, 2025).
@inproceedings{asimopoulos2025hybrid,
title = {Hybrid-FGPG: A Novel Fusion of Gradient and Geometric Transformations for Adversarial Vulnerability Evaluation},
author = {Dimitrios-Christos Asimopoulos, Panagiotis Radoglou-Grammatikis, Vasileios Argyriou, Thomas Lagkas, Pantelis Angelidis, Vasileios Vitsas, Panagiotis Fouliras, Ioannis Ktenidis, Panagiotis Sarigiannidis},
year = {2025},
date = {2025-12-01},
urldate = {2025-12-01},
booktitle = {IEEE Global Communications Conference (GLOBECOM) Workshops},
address = {Taipei, Taiwan},
abstract = {This paper contributes to the area of AI attacks and cybersecurity, focusing on adversarial vulnerability evaluation through a novel hybrid approach combining gradient and geometric transformations (Hybrid-FGPG). The research leverages communication, softwarization, and machine learning for IoT services, particularly within 6G and cloud/fog/edge computing environments, aiming to evaluate and enhance the resilience of AI-driven IoT systems against advanced security threats.},
note = {Presented at WS-18: The Third Workshop on SIGNIS: Softwarized Next Generation Networks for IoT Services, December 8–12, 2025},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper contributes to the area of AI attacks and cybersecurity, focusing on adversarial vulnerability evaluation through a novel hybrid approach combining gradient and geometric transformations (Hybrid-FGPG). The research leverages communication, softwarization, and machine learning for IoT services, particularly within 6G and cloud/fog/edge computing environments, aiming to evaluate and enhance the resilience of AI-driven IoT systems against advanced security threats.