@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}

}