Adversarial Machine Learning Threats to Spacecraft

TL;DR

This paper explores the vulnerabilities of spacecraft to adversarial machine learning attacks, demonstrating potential threats through simulations and emphasizing the need for AML-specific security measures in autonomous space systems.

Contribution

It introduces a threat taxonomy for AML in spacecraft and demonstrates attack execution via simulations, highlighting security implications for autonomous space systems.

Findings

AML attacks can successfully disrupt spacecraft operations

Simulations show vulnerabilities in NASA's core flight systems

Security measures must address AML threats in space autonomy

Abstract

Spacecraft are among the earliest autonomous systems. Their ability to function without a human in the loop have afforded some of humanity's grandest achievements. As reliance on autonomy grows, space vehicles will become increasingly vulnerable to attacks designed to disrupt autonomous processes-especially probabilistic ones based on machine learning. This paper aims to elucidate and demonstrate the threats that adversarial machine learning (AML) capabilities pose to spacecraft. First, an AML threat taxonomy for spacecraft is introduced. Next, we demonstrate the execution of AML attacks against spacecraft through experimental simulations using NASA's Core Flight System (cFS) and NASA's On-board Artificial Intelligence Research (OnAIR) Platform. Our findings highlight the imperative for incorporating AML-focused security measures in spacecraft that engage autonomy.