A Non-Line-of-Sight, Multi-Modality-based Side-Channel IP Theft Attack on Additive Manufacturing Using Dual Smartphones

Jul 16, 2026

Upload by Logic

Additive Manufacturing (AM) enables flexible production across sectors, but its printing process can leak Intellectual Property (IP) through unintended side-channel emissions. Prior 3D-printer attacks struggle with low G-code reconstruction accuracy, limited attack distance, and dependence on specialized data-collection tools. This work proposes a practical multi-modal side-channel attack using two smartphones’ microphones and magnetometers placed 60 cm away in a non-line-of-sight setup to capture acoustic and magnetic signals. The method reconstructs final objects’ G-code with 98.89% command-level accuracy and evaluates transferability across environments while discussing mitigations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

Introduction

Additive manufacturing benefits and adoption

Vulnerability to side-channel attacks

Practical attacker model and multi-modal smartphone sensing

A Non-Line-of-Sight, Multi-Modality-based Side-Channel IP Theft Attack on Additive Manufacturing Using Dual Smartphones Amirhossein Jamarani∗ , Diba Afroze∗ , Yazhou Tu†, Mark Yampolskiy†, Xiali Hei∗ ∗ University of Louisiana at Lafayette, Lafayette, LA, USA Email: {amirhossein.jamarani1, diba.afroze1, [xiali.hei](xiali.hei}@louisiana.edu)[}](xiali.hei}@louisiana.edu)[@louisiana.edu](xiali.hei}@louisiana.edu) †Auburn University, Auburn, AL, USA Email: {yzt0065, [mzy0033](mzy0033}@auburn.edu)[}](mzy0033}@auburn.edu)[@auburn.edu](mzy0033}@auburn.edu) arXiv :2607 .00186v1 [ cs .CR] 30 Jun 2026 Abstract—Additive Manufacturing (AM) has revolutionized major sectors, including aerospace, automotive, and healthcare, by enabling adjustable production. As the usage of AM increases, so does the risk of Intellectual Property (IP) leakage during the printing process due to unintended side-channel emissions. Current studies and attack scenarios on 3D printers face three challenges: low success and accuracy rates in final G-code reconstruction, limited distance range for attacking the 3D printer’s IP, and reliance on specialized, overt data-collection tools. This paper presents a side-channel attack that addresses the noted limitations by using two smartphones’ internal sensors. We position the smartphones 60 cm away in a non-line-of-sight setup to collect the 3D printer’s acoustic and magnetic emissions. Our attack successfully reconstructs the G-code commands of the final objects at the rate of 98.89% on command-level reconstruction accuracy. Additionally, we evaluate the transferability of our attack strategy by applying it to another 3D printer in a different environment. Our proven unauthorized access to thereconstructed G-code and thus to the IP of the AM system indicates the security weaknesses in 3D printing, highlighting the need for mitigating side-channel attacks. I. INTRODUCTION Additive Manufacturing (AM), commonly referred to as 3D printing, has reshaped how products are designed, prototyped, and manufactured [1], [2] . By enabling rapid prototyping, ondemand production, and the fabrication of complex geometries that are difficult to achieve with conventional subtractive processes, AM has become an important driver of innovation across multiple sectors [3] . In parallel, advances in AM education and design-for-AM tools have led to the transition of 3D printing from primarily visualization and prototyping to industrial-grade production workflows [4], [5] . This transition is frequently associated with shorter development cycles, reduced material waste, lower production costs for suitable part classes, and increased opportunities for personalization [6]–[8] . Consequently, 3D printing has been adopted in domains such as aerospace [9], healthcare [10], automotive [11], construction [12], and food printing [13] . The accessibility of modern printers, combined with widely available documentation and increasingly user-friendly software stacks, has further supported this adoption [14]–[16] . Fig. 1. End-to-end attack workflow showing how acoustic and magnetic emissions from a 3D printer are captured, processed, and used to reconstruct the underlying G-code in our study. Despite these benefits, the 3D printing process is vulnerable to side-channel attacks. Prior studies [17]–[22] have shown that G-code instructions can be partially reconstructed by exploiting unintended emissions, including acoustic and magnetic signals produced during printer operation. However, many existing evaluations rely on assumptions that can be difficult to justify outside controlled settings. These assumptions often include: (i) close-range smartphone placement within direct line-of-sight of less than 30 cm or usage of specialized data-collection equipment [17],[22]–[24](ii) simplified operational behavior in which the printer is assumed to execute only printing motions, while non-print states, for example, cooling cycles, idle periods,

FAQs

What security weakness does the paper target in additive manufacturing?

The paper targets IP leakage caused by unintended side-channel emissions during 3D printing, which can be exploited to recover underlying G-code instructions.

How does the proposed attack capture signals without line-of-sight?

It conceals two smartphones and uses their built-in microphones and magnetometers to collect acoustic and magnetic emissions while positioned non-line-of-sight.

What reconstruction performance does the attack achieve, and is it transferable?

It achieves 98.89% command-level reconstruction accuracy for final objects and evaluates transferability by applying the strategy to another 3D printer in a different environment.

Jul 16, 2026

Upload by Logic