Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing

TL;DR

This paper introduces FI-LDP-HGAT, a novel framework combining hierarchical graph attention networks and feature-importance-aware anisotropic Gaussian mechanisms to enhance utility in privacy-preserving graph learning for metal additive manufacturing.

Contribution

It proposes a new anisotropic privacy mechanism that allocates noise based on feature importance, improving utility while maintaining formal differential privacy guarantees.

Findings

Achieves 81.5% utility recovery at epsilon=4.

Maintains defect recall of 0.762 under strict privacy (epsilon=2).

Outperforms classical ML, standard GNNs, and other privacy mechanisms.

Abstract

Metal additive manufacturing (AM) enables the fabrication of safety-critical components, but reliable quality assurance depends on high-fidelity sensor streams containing proprietary process information, limiting collaborative data sharing. Existing defect-detection models typically treat melt-pool observations as independent samples, ignoring layer-wise physical couplings. Moreover, conventional privacy-preserving techniques, particularly Local Differential Privacy (LDP), lead to severe utility degradation because they inject uniform noise across all feature dimensions. To address these interrelated challenges, we propose FI-LDP-HGAT. This computational framework combines two methodological components: a stratified Hierarchical Graph Attention Network (HGAT) that captures spatial and thermal dependencies across scan tracks and deposited layers, and a feature-importance-aware anisotropic Gaussian mechanism (FI-LDP) for non-interactive feature privatization. Unlike isotropic LDP, FI-LDP redistributes the privacy budget across embedding coordinates using an encoder-derived importance prior, assigning lower noise to task-critical thermal signatures and higher noise to redundant dimensions while maintaining formal LDP guarantees. Experiments on a Directed Energy Deposition (DED) porosity dataset demonstrate that FI-LDP-HGAT achieves 81.5% utility recovery at a moderate privacy budget (epsilon = 4) and maintains defect recall of 0.762 under strict privacy (epsilon = 2), while outperforming classical ML, standard GNNs, and alternative privacy mechanisms, including DP-SGD across all evaluated metrics. Mechanistic analysis confirms a strong negative correlation (Spearman = -0.81) between feature importance and noise magnitude, providing interpretable evidence that the privacy-utility gains are driven by principled anisotropic allocation.