Title:
NETWORK TRAFFIC CHARACTERIZATION AND INTRUSION DETECTION IN BUILDING AUTOMATION SYSTEMS
NETWORK TRAFFIC CHARACTERIZATION AND INTRUSION DETECTION IN BUILDING AUTOMATION SYSTEMS
| dc.contributor.advisor | Beyah, Raheem A. | |
| dc.contributor.author | Irvene, Celine | |
| dc.contributor.committeeMember | Cardenas, Alvaro | |
| dc.contributor.committeeMember | Lerner, Lee | |
| dc.contributor.committeeMember | Copeland, John | |
| dc.contributor.committeeMember | Shelden, Dennis | |
| dc.contributor.department | Electrical and Computer Engineering | |
| dc.date.accessioned | 2022-08-25T13:25:54Z | |
| dc.date.available | 2022-08-25T13:25:54Z | |
| dc.date.created | 2021-08 | |
| dc.date.issued | 2021-05-19 | |
| dc.date.submitted | August 2021 | |
| dc.date.updated | 2022-08-25T13:25:55Z | |
| dc.description.abstract | The goal of this research was threefold: (1) to learn the operational trends and behaviors of a realworld building automation system (BAS) network for creating building device models to detect anomalous behaviors and attacks, (2) to design a framework for evaluating BA device security from both the device and network perspectives, and (3) to leverage new sources of building automation device documentation for developing robust network security rules for BAS intrusion detection systems (IDSs). These goals were achieved in three phases, first through the detailed longitudinal study and characterization of a real university campus building automation network (BAN) and with the application of machine learning techniques on field level traffic for anomaly detection. Next, through the systematization of literature in the BAS security domain to analyze cross protocol device vulnerabilities, attacks, and defenses for uncovering research gaps as the foundational basis of our proposed BA device security evaluation framework. Then, to evaluate our proposed framework the largest multiprotocol BAS testbed discussed in the literature was built and several side-channel vulnerabilities and software/firmware shortcomings were exposed. Finally, through the development of a semi-automated specification gathering, device documentation extracting, IDS rule generating framework that leveraged PICS files and BIM models. | |
| dc.description.degree | Ph.D. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1853/67103 | |
| dc.publisher | Georgia Institute of Technology | |
| dc.subject | CPS, BAS, security, smart building | |
| dc.title | NETWORK TRAFFIC CHARACTERIZATION AND INTRUSION DETECTION IN BUILDING AUTOMATION SYSTEMS | |
| dc.type | Text | |
| dc.type.genre | Dissertation | |
| dspace.entity.type | Publication | |
| local.contributor.advisor | Beyah, Raheem A. | |
| local.contributor.corporatename | School of Electrical and Computer Engineering | |
| local.contributor.corporatename | College of Engineering | |
| relation.isAdvisorOfPublication | 88360599-cf62-474a-81dd-961af8abbb9b | |
| relation.isOrgUnitOfPublication | 5b7adef2-447c-4270-b9fc-846bd76f80f2 | |
| relation.isOrgUnitOfPublication | 7c022d60-21d5-497c-b552-95e489a06569 | |
| thesis.degree.level | Doctoral |