Adversarial Machine Learning Threats to Spacecraft

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thummala, Rajiv, Sharma, Shristi, Calabrese, Matteo, Falco, Gregory
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909203067568128
author Thummala, Rajiv
Sharma, Shristi
Calabrese, Matteo
Falco, Gregory
author_facet Thummala, Rajiv
Sharma, Shristi
Calabrese, Matteo
Falco, Gregory
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08834
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Machine Learning Threats to Spacecraft
Thummala, Rajiv
Sharma, Shristi
Calabrese, Matteo
Falco, Gregory
Machine Learning
Artificial Intelligence
Cryptography and Security
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.
title Adversarial Machine Learning Threats to Spacecraft
topic Machine Learning
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2405.08834