{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-4672"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-4672","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Analysis of Deep Learning Methods for Wired Ethernet Physical Layer Security of Operational Technology","abstract":"The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at the physical layer or Layer 1 of the OSI model. The security model collects signal data from Ethernet device transmissions, applies deep learning to gather distinguishing features from signal data, and uses these features to make an authentication decision on the Ethernet devices. The proposed approach is passive, automatic, and spoof-resistant. The role of deep learning is critical to the security model. This thesis will look at analyzing and improving deep learning at each step of the security model including data processing, model training, model efficiency, transfer learning on new devices, and device authentication.","abstract_html":"The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at the physical layer or Layer 1 of the OSI model. The security model collects signal data from Ethernet device transmissions, applies deep learning to gather distinguishing features from signal data, and uses these features to make an authentication decision on the Ethernet devices. The proposed approach is passive, automatic, and spoof-resistant. The role of deep learning is critical to the security model. This thesis will look at analyzing and improving deep learning at each step of the security model including data processing, model training, model efficiency, transfer learning on new devices, and device authentication.","abstract_has_math":false,"creators":["Torlay, Lucas"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Dr. Johan Enslin","Dr. Bill Suski","Dr. Harlan Russell"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:28:57Z","subjects":["Deep Learning","Operational Technology","Physical Layer","Cybersecurity","Machine Learning","Data Science","Information Security","Other Electrical and Computer Engineering","Power and Energy","Signal Processing","Systems and Communications"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/3696","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/3696","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-4672","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Johan Enslin","Dr. Bill Suski","Dr. Harlan Russell"]},{"key":"dc:creator","label":"Author","values":["Torlay, Lucas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2021-11-30T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2021-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Operational Technology","Physical Layer","Cybersecurity","Machine Learning","Data Science","Information Security","Other Electrical and Computer Engineering","Power and Energy","Signal Processing","Systems and Communications"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/3696"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at the physical layer or Layer 1 of the OSI model. The security model collects signal data from Ethernet device transmissions, applies deep learning to gather distinguishing features from signal data, and uses these features to make an authentication decision on the Ethernet devices. The proposed approach is passive, automatic, and spoof-resistant. The role of deep learning is critical to the security model. This thesis will look at analyzing and improving deep learning at each step of the security model including data processing, model training, model efficiency, transfer learning on new devices, and device authentication."]},{"key":"dc:title","label":"Title","values":["Analysis of Deep Learning Methods for Wired Ethernet Physical Layer Security of Operational Technology"]}]}],"canonical_facts":{"dc:contributor":["Dr. Johan Enslin","Dr. Bill Suski","Dr. Harlan Russell"],"dc:creator":["Torlay, Lucas"],"dc:date.available":["2021-11-30T08:00:00Z"],"dc:date.created":["2021-12-01T08:00:00Z"],"dc:description.abstract":["The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at the physical layer or Layer 1 of the OSI model. The security model collects signal data from Ethernet device transmissions, applies deep learning to gather distinguishing features from signal data, and uses these features to make an authentication decision on the Ethernet devices. The proposed approach is passive, automatic, and spoof-resistant. The role of deep learning is critical to the security model. This thesis will look at analyzing and improving deep learning at each step of the security model including data processing, model training, model efficiency, transfer learning on new devices, and device authentication."],"dc:identifier":["https://open.clemson.edu/all_theses/3696"],"dc:subject":["Deep Learning","Operational Technology","Physical Layer","Cybersecurity","Machine Learning","Data Science","Information Security","Other Electrical and Computer Engineering","Power and Energy","Signal Processing","Systems and Communications"],"dc:title":["Analysis of Deep Learning Methods for Wired Ethernet Physical Layer Security of Operational Technology"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:28:57Z"}