Extraction and Analysis of Spatial Correlation Micrograph Features for Traceability in Manufacturing
Abstract We propose a method for ensuring traceability of metal goods in an efficient and secure manner that leverages data obtained from micrographs of a part’s surface that is instance-specific (i.e., different for another instance of that same part). All stakeholders in modern supply chains face a growing need to ensure quality and trust in the goods they produce. Complex supply chains open many opportunities for counterfeiters, saboteurs, or other attackers to infiltrate supply networks, and existing methods for preventing such attacks can be costly, invasive, and ineffective. The proposed method extracts discriminatory-yet-robust intrinsic strings using features extracted from two-point autocorrelation data of surface microstructures. Using a synthetic dataset of three-phase micrographs similar to those obtained from metal alloy systems using low-cost optical microscopy techniques, we discuss the optimization of the method with respect to cost and security, and discuss the performance of the method in the context of anti-counterfeiting. Cryptographic extensions of this methodology are also discussed.