Aggregation of Heterogeneous Anomaly Detectors for Cyber-Physical Systems

anomaly detection;cyber-physical systems

Dunne, Murrayadvisor:Fischmeister, Sebastian ; affiliation1:Faculty of Mathematics ; Fischmeister, Sebastian ;

University of Waterloo

关键词: cyber-physical systems;    Master Thesis;    anomaly detection;   

Others  :  https://uwspace.uwaterloo.ca/bitstream/10012/14318/3/Dunne_Murray.pdf

瑞士|英语

来源: UWSPACE Waterloo Institutional Repository

【 摘 要 】

Distributed, life-critical systems that bridge the gap between software and hardwareare becoming an integral part of our everyday lives. From autonomous cars to smartelectrical grids, such cyber-physical systems will soon be omnipresent. With this comes acorresponding increase in our vulnerability to cyber-attacks. Monitoring such systems todetect malicious actions is of critical importance.One method of monitoring cyber-physical systems is anomaly detection: the process ofdetecting when the target system is deviating from expected normal behavior. Anomalydetection is a vibrant research area with many different viable approaches. The literaturesuggests many different anomaly detection methods for the diversity and volume of datafrom cyber-physical systems. We focus on aggregating the result of multiple anomalydetection methods into a final anomalous or non-anomalous verdict.In this thesis, we present Palisade, a distributed data collection, anomaly detection,and aggregation framework for cyber-physical systems. We discuss various methods ofanomaly detection and aggregation and include a case study of anomaly aggregation on acyber-physical treadmill driving demonstrator. We conclude with a discussion of lessonslearned from the construction of Palisade, and recommendations for future research.