Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bozkurt, Alper Kamil, Wang, Yu, Pajic, Miroslav
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913002298540032
author Bozkurt, Alper Kamil
Wang, Yu
Pajic, Miroslav
author_facet Bozkurt, Alper Kamil
Wang, Yu
Pajic, Miroslav
contents We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the controller as well as the employed intrusion-detection system and who wants to prevent the controller from performing tasks while staying stealthy. We formulate the problem as a stochastic game between the attacker and the controller and present an approach to express the objective of such an agent and the controller as a combined linear temporal logic (LTL) formula. We then show that the planning problem, described formally as the problem of satisfying an LTL formula in a stochastic game, can be solved via model-free reinforcement learning when the environment is completely unknown. Finally, we illustrate and evaluate our methods on two robotic planning case studies.
format Preprint
id arxiv_https___arxiv_org_abs_2011_01882
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning
Bozkurt, Alper Kamil
Wang, Yu
Pajic, Miroslav
Robotics
Computer Science and Game Theory
We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the controller as well as the employed intrusion-detection system and who wants to prevent the controller from performing tasks while staying stealthy. We formulate the problem as a stochastic game between the attacker and the controller and present an approach to express the objective of such an agent and the controller as a combined linear temporal logic (LTL) formula. We then show that the planning problem, described formally as the problem of satisfying an LTL formula in a stochastic game, can be solved via model-free reinforcement learning when the environment is completely unknown. Finally, we illustrate and evaluate our methods on two robotic planning case studies.
title Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning
topic Robotics
Computer Science and Game Theory
url https://arxiv.org/abs/2011.01882