Turning Hearsay into Discovery: Industrial 3D Printer Side Channel Information Translated to Stealing the Object Design

2025-09-22

AI Summary

This work uncovers a novel side-channel security threat to digital designs in industrial-scale powder-bed fusion (PBF) 3D printers: even when design files are end-to-end encrypted, remote power consumption measurements during printing enable full 3D model reconstruction. We introduce the first application of multi-trace differential power analysis (DPA) to additive manufacturing, proposing an attack framework that jointly performs power feature extraction and voxel-level 3D reconstruction. Unlike prior studies limited to desktop FDM systems, our method achieves end-to-end model recovery on authentic industrial PBF hardware. Experimental evaluation demonstrates high fidelity: 90.29% true positive rate, 7.02% false positive rate, and 9.71% false negative rate across models of varying complexity. These results validate both the efficacy and practical feasibility of the attack, establishing critical empirical evidence and a new research paradigm for securing additive manufacturing systems.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Hardware-aware ML

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

The central security issue of outsourced 3D printing (aka AM: Additive Manufacturing), an industry that is expected to dominate manufacturing, is the protection of the digital design (containing the designers' model, which is their intellectual property) shared with the manufacturer. Here, we show, for the first time, that side-channel attacks are, in fact, a concrete serious threat to existing industrial grade 3D printers, enabling the reconstruction of the model printed (regardless of employing ways to directly conceal the design, e.g. by encrypting it in transit and before loading it into the printer). Previously, such attacks were demonstrated only on fairly simple FDM desktop 3D printers, which play a negligible role in manufacturing of valuable designs. We focus on the Powder Bed Fusion (PBF) AM process, which is popular for manufacturing net-shaped parts with both polymers and metals. We demonstrate how its individual actuators can be instrumented for the collection of power side-channel information during the printing process. We then present our approach to reconstruct the 3D printed model solely from the collected power side-channel data. Further, inspired by Differential Power Analysis, we developed a method to improve the quality of the reconstruction based on multiple traces. We tested our approach on two design models with different degrees of complexity. For different models, we achieved as high as 90.29~% of True Positives and as low as 7.02~% and 9.71~% of False Positives and False Negatives by voxel-based volumetric comparison between reconstructed and original designs. The lesson learned from our attack is that the security of design files cannot solely rely on protecting the files themselves in an industrial environment, but must instead also rely on assuring no leakage of power, noise and similar signals to potential eavesdroppers in the printer's vicinity.

Problem

• Protecting intellectual property in industrial 3D printing from side-channel attacks
• Reconstructing 3D printed models using power consumption data from printers
• Addressing security vulnerabilities in industrial Powder Bed Fusion manufacturing

Innovation

• Using power side-channel attacks on industrial 3D printers
• Reconstructing 3D models from collected power consumption data
• Improving reconstruction quality with differential power analysis