Cyber-Physical Anomaly Detection in Microgrids Using Time-Frequency Logic Formalism

Autor: Omar Ali Beg, Luan Viet Nguyen, Taylor T. Johnson, Ali Davoudi

Publikováno v: IEEE Access, Vol 9, Pp 20012-20021 (2021)

Modern cyber-physical microgrids rely on the information exchanged among power electronics devices (i.e., converters or inverters with local embedded controllers) making them vulnerable to cyber manipulations. The physical devices themselves are susc

Externí odkaz: https://doaj.org/article/39f7d634b5554ed89af41c5c59105f0f

DEMO: Self-Preserving Genetic Algorithms vs. Safe Reinforcement Learning in Discrete Action Spaces

Autor: Preston K. Robinette, Nathaniel P. Hamilton, Taylor T. Johnson

Publikováno v: Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::05fba54241acf9b0ace89de5ef2b5691
https://doi.org/10.1145/3576841.3589635

Verification Approaches for Learning-Enabled Autonomous Cyber–Physical Systems

Autor: Hoang-Dung Tran, Taylor T. Johnson, Weiming Xiang

Publikováno v: IEEE Design & Test. 39:24-34

This paper presents an overview survey of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof. Autonomy in CPS is enabled by recent advances in artificial i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8041b2a15786ec76b8b5c06f2c848e5c
https://doi.org/10.1109/mdat.2020.3015712

ARCH-COMP22 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

Autor: Diego Manzanas Lopez, Matthias Althoff, Luis Benet, Xin Chen, Jiameng Fan, Marcelo Forets, Chao Huang, Taylor T Johnson, Tobias Ladner, Wenchao Li, Christian Schilling, Qi Zhu

Publikováno v: Lopez, D M, Althoff, M, Benet, L, Chen, X, Fan, J, Forets, M, Huang, C, Johnson, T T, Ladner, T, Li, W, Schilling, C & Zhu, Q 2022, ARCH-COMP22 category report: Artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants . in G Frehse, M Althoff, E Schoitsch & J Guiochet (eds), 9th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH22) . EasyChair, EPiC Series in Computing, vol. 90, pp. 142-184, 9th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH22), Munich, Germany, 06/09/2022 . https://doi.org/10.29007/wfgr

This report presents the results of a friendly competition for formal verification of continuous and hybrid systems with artificial intelligence (AI) components. Specifically, machine learning (ML) components in cyber-physical systems (CPS), such as

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f14458daeccc4f4b6f6e5f712cd1895
https://doi.org/10.29007/wfgr

Verification of piecewise deep neural networks: a star set approach with zonotope pre-filter

Autor: Luan Viet Nguyen, Stanley Bak, Neelanjana Pal, Weiming Xiang, Xiaodong Yang, Taylor T. Johnson, Patrick Musau, Diego Manzanas Lopez, Hoang-Dung Tran

Publikováno v: Formal Aspects of Computing. 33:519-545

Verification has emerged as a means to provide formal guarantees on learning-based systems incorporating neural network before using them in safety-critical applications. This paper proposes a new verification approach for deep neural networks (DNNs)

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::35886cccc5a5e832422ded3eefabe952
https://doi.org/10.1007/s00165-021-00553-4