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

نویسندگان

چکیده

High performance but unverified controllers, e.g., artificial intelligence-based (a.k.a. AI-based) are widely employed in cyber–physical systems (CPSs) to accomplish complex control missions. However, guaranteeing the safety and reliability of CPSs with this kind controllers is currently very challenging, which vital importance many real-life safety-critical applications. To cope difficulty, we propose work a Safe-visor architecture for sandboxing operating noisy environments stochastic CPSs). The proposed contains history-based supervisor, checks inputs from controller makes compromise between functionality system, advisor that provides fallback when endangers system. Both supervisor designed based on an approximate probabilistic relation original system its finite abstraction. By employing architecture, provide formal guarantees preserving specifications expressed by accepting languages deterministic automata (DFA). Meanwhile, can still be loop even though they not reliable. We demonstrate effectiveness our results applying them two (physical) case studies.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SMT-based Synthesis of Safe and Robust PID Controllers for Stochastic Hybrid Systems

We present a new method for the automated synthesis of safe and robust Proportional-Integral-Derivative (PID) controllers for stochastic hybrid systems. Despite their widespread use in industry, no automated method currently exists for deriving a PID controller (or any other type of controller, for that matter) with safety and performance guarantees for such a general class of systems. In parti...

متن کامل

A Hardware Virtualization Based Component Sandboxing Architecture

Modern applications comprise multiple components, such as browser plug-ins, often of unknown provenance and quality. Statistics show that failure of such components accounts for a high percentage of software faults. Enabling isolation of such fine-grained components is therefore necessary to increase the robustness and resilience of security-critical and safety-critical computer systems. In thi...

متن کامل

User-Level Sandboxing: a Safe and Efficient Mechanism for Extensibility

Extensible systems allow services to be configured and deployed for the specific needs of individual applications. This paper describes a safe and efficient method for userlevel extensibility that requires only minimal changes to the kernel. A sandboxing technique is described that supports multiple logical protection domains within the same address space at user-level. This approach allows app...

متن کامل

Transaction-based Sandboxing for JavaScript

Today’s JavaScript applications are composed of scripts from different origins that are loaded at run time. As not all of these origins are equally trusted, the execution of these scripts should be isolated from one another. However, some scripts must access the application state and some may be allowed to change it, while preserving the confidentiality and integrity constraints of the applicat...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Nonlinear Analysis: Hybrid Systems

سال: 2021

ISSN: ['1751-570X', '1878-7460']

DOI: https://doi.org/10.1016/j.nahs.2021.101110