Bai, HeThornton, CollinWentz Research Scholars2020-07-072020-07-072020-04-24Thornton, C., & Bai, H. (2020, April 24). Security for autonomous cyber-physical systems. Poster session presented at the Oklahoma State University Wentz Research Scholars Symposium, Stillwater, OK.https://hdl.handle.net/20.500.14446/324947Remote disablement and control of autonomous cyber-physical systems is possible through the external manipulation of sensory subsystems. Many modern autonomous systems utilize neural networks to fuse and parse data from sensor input streams. We suggest that the application of probabilistic neural network models increases the robustness of machine learning in sensory subsystems. This study compares Probabilistic Backpropagation (PBP) and equivalently sized non-probabilistic models at processing datasets injected with normally distributed noise. Our results suggest that PBP performs with a smaller RMSE and that its estimate of the posterior uncertainty of weights provides insight to the trustworthiness of the model.application/pdfIn the Oklahoma State University Library's institutional repository this paper is made available through the open access principles and the terms of agreement/consent between the author(s) and the publisher. The permission policy on the use, reproduction or distribution of the article falls under fair use for educational, scholarship, and research purposes. Contact Digital Resources and Discovery Services at lib-dls@okstate.edu or 405-744-9161 for further information.Presentationneural networksprobabilistic neural networksrobotics