An NYU Tandon School of Engineering study has raised concerns on the security of intellectual property in 3D printed composite parts.
According to the scientists led by professor Nikhil Gupta, 3D printing toolpaths (a series of coordinated locations a tool will follow) are easy to reproduce – and therefore steal – when reversed engineered.
This can be done with the help of Machine Learning (ML) tools when applied to the microstructures of the part obtained by a CT scan.
The use of glass- and carbon- fiber reinforced composites in aerospace and other high-performance applications has soared in recent years.
Integral to the strength and versatility of these materials in high-performance applications is the orientation of fibers in each layer.
Recent innovations in additive manufacturing have made it possible to fine-tune this factor, thanks to the ability to include within the CAD file discrete printer-head orientation instructions for each layer of the component being printed.
This helps optimize strength, flexibility, and durability for specific uses of the part.
Such 3D printing toolpaths in CAD file instructions are therefore a valuable trade secret for the manufacturers – and also a treasure trove for hackers.
That’s exactly what Gupta’s team strove to prove by reverse engineering a 3D printed glass-fiber reinforced polymer filament that, when 3D printed, has a dimensional accuracy within one-third of 1% of the original part.
The investigators – graduate students Kaushik Yanamandra, Guan Lin Chen, Xianbo Xu, and Gary Mac – have shown that the printing direction used during the 3D-printing process can be captured from the printed part’s fiber orientation via micro-CT scan image.
Since the fiber direction is difficult to discern with the naked eye, the team used ML algorithms trained over thousands of micro CT scan images to predict the fiber orientation on any fiber-reinforced 3D printed model.
They then validated their ML algorithm results on cylinder- and square-shaped models finding less than 0.5° error.
Gupta concludes that the study’s results show that security concerns should be addressed during the design process and ‘unclonable’ toolpaths must be developed to keep hackers at bay.
Image and content: Arevo/NYU Tandon School of Engineering