Adversarial Examples for Model-Based Control: A Sensitivity Analysis

TL;DR

This paper introduces a method to perform adversarial attacks on model-based controllers by manipulating external timeseries, significantly increasing control costs and constraint violations in power grid applications.

Contribution

It presents a novel approach to attack controllers using forged timeseries, revealing vulnerabilities in safety-critical control systems.

Findings

Control costs increased by 8500%

Energy constraints violated by 13%

Effective attack demonstrated on power grid control

Abstract

We propose a method to attack controllers that rely on external timeseries forecasts as task parameters. An adversary can manipulate the costs, states, and actions of the controllers by forging the timeseries, in this case perturbing the real timeseries. Since the controllers often encode safety requirements or energy limits in their costs and constraints, we refer to such manipulation as an adversarial attack. We show that different attacks on model-based controllers can increase control costs, activate constraints, or even make the control optimization problem infeasible. We use the linear quadratic regulator and convex model predictive controllers as examples of how adversarial attacks succeed and demonstrate the impact of adversarial attacks on a battery storage control task for power grid operators. As a result, our method increases control cost by $8500\%$ and energy constraints by $13\%$ on real electricity demand timeseries.