Paper Info
Title
Acoustic Side-Channel Attacks on Additive Manufacturing Systems.
Abstract
Additive manufacturing systems, such as 3D printers, emit sounds while creating objects. Our work demonstrates that these sounds carry process information that can be used to indirectly reconstruct the objects being printed, without requiring access to the original design. This is an example of a physical-to-cyber domain attack, where information gathered from the physical domain, such as acoustic side-channel, can be used to reveal information about the cyber domain. Our novel attack model consists of a pipeline of audio signal processing, machine learning algorithms, and context-based post-processing to improve the accuracy of the object reconstruction. In our experiments, we have successfully reconstructed the test objects (designed to test the attack model under various benchmark parameters) and their corresponding G-codes with an average accuracy for axis prediction of 78.35% and an average length prediction error of 17.82% on a Fused Deposition Modeling (FDM) based additive manufacturing system. Our work exposes a serious vulnerability in FDM based additive manufacturing systems exploitable by physical-to-cyber attacks that may lead to theft of Intellectual Property (IP) and trade secrets. To the best of our knowledge this kind of attack has not yet been explored in additive manufacturing systems.
Year
DOI
Venue
2016
10.1109/ICCPS.2016.7479068
ICCPS
Keywords
Field
DocType
Side-Channel Attack,Security,Additive Manufacturing Systems,3D Printer,Cyber-Physical Systems
3d printer,Attack model,Mean squared prediction error,Manufacturing systems,Computer science,Real-time computing,Cyber-physical system,Fused deposition modeling,Side channel attack,Audio signal processing
Conference
ISSN
Citations 
PageRank 
2375-8317
22
1.67
References 
Authors
6
4
Name
Order
Citations
PageRank
Mohammad Abdullah Al Faruque162765.35
Sujit Rokka Chhetri2505.76
Arquimedes Canedo314323.31
Jiang Wan4455.63