Sandboxing controllers for stochastic cyber-physical systems

DOI10.1007/978-3-030-29662-9_15zbMATH Open1441.93298arXiv2109.11264OpenAlexW2969446727MaRDI QIDQ2176707FDOQ2176707

Authors: Bingzhuo Zhong, Majid Zamani, Marco Caccamo 

Publication date: 5 May 2020

Abstract: Current cyber-physical systems (CPS) are expected to accomplish complex tasks. To achieve this goal, high performance, but unverified controllers (e.g. deep neural network, black-box controllers from third parties) are applied, which makes it very challenging to keep the overall CPS safe. By sandboxing these controllers, we are not only able to use them but also to enforce safety properties over the controlled physical systems at the same time. However, current available solutions for sandboxing controllers are just applicable to deterministic (a.k.a. non-stochastic) systems, possibly affected by bounded disturbances. In this paper, for the first time we propose a novel solution for sandboxing unverified complex controllers for CPS operating in noisy environments (a.k.a. stochastic CPS). Moreover, we also provide probabilistic guarantees on their safety. Here, the unverified control input is observed at each time instant and checked whether it violates the maximal tolerable probability of reaching the unsafe set. If this probability exceeds a given threshold, the unverified control input will be rejected, and the advisory input provided by the optimal safety controller will be used to maintain the probabilistic safety guarantee. The proposed approach is illustrated empirically and the results indicate that the expected safety probability is guaranteed.

Full work available at URL: https://arxiv.org/abs/2109.11264

Recommendations

• Control barrier functions for stochastic systems
• A barrier function approach to finite-time stochastic system verification and control
• Learning safe neural network controllers with barrier certificates
• Checking scheduling-induced violations of control safety properties
• Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions

zbMATH Keywords

fault-tolerancestochastic cyber-physical systemssandboxing controllers

Mathematics Subject Classification ID

Stochastic systems in control theory (general) (93E03) Control/observation systems involving computers (process control, etc.) (93C83) Computer security (68M25) Networked control (93B70)

Cited In (1)

• Safe-visor architecture for sandboxing (AI-based) unverified controllers in stochastic cyber-physical systems

This page was built for publication: Sandboxing controllers for stochastic cyber-physical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2176707)