Thesis
Detecting malicious data in phasor data streams
Washington State University
Master of Science (MS), Washington State University
2019
Handle:
https://hdl.handle.net/2376/102968
Abstract
Phasor Measurement Units (PMUs) provide high-quality state information about the electrical grid in near-real time. However, as utilities become more reliant on these measurements, the devices themselves as well as the communication network that supports them will likely become a more prominent attack surface for cyber threats. In this paper, we demonstrate a system designed to find anomalous PMU data-specifically data that is intended to provide false signal readings (spoofed data) over a period of time. Our system uses support vector machines to distinguish between "normal" system operation and "spoofed" operation. The work presented here makes four main contributions: (1) we demonstrate that a SVM trained on one specific type of spoof can be used to identify a variety of different spoof strategies with high accuracy; (2) we demonstrate that our system has reasonable longevity (i.e., once trained, the classifier remains valid for a reasonable length of time); (3) we demonstrate how the classifiers can be modified to detect episodes of spoofs instead of detecting individual spoofed cycles; Based on this method, we further investigate the trade-offs between detection latency and classifiers' performance. Additionally, we provide a performance analysis using different notions of accuracy and compare the results. (4) we develop a distributed version of our algorithm that runs several smaller classifiers in parallel to improve the system efficiency and scalability.
Metrics
14 File views/ downloads
6 Record Views
Details
- Title
- Detecting malicious data in phasor data streams
- Creators
- Xuan Liu
- Contributors
- Scott Andrew Wallace (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525062001842
- Language
- English
- Resource Type
- Thesis