Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring

2024-07-09

AI Summary

To address privacy leakage risks of design and material data in machine learning–based in-situ monitoring for additive manufacturing, this paper proposes DP-HD—a novel framework integrating differential privacy (DP) and hyperdimensional computing (HDC) to jointly enhance privacy protection and model interpretability. Methodologically, we introduce signal-to-noise ratio (SNR) to quantify the impact of DP noise on model accuracy; further, by synergizing eXplainable AI (XAI) with the HDC vector-symbol paradigm, we enable interpretable, privacy-accuracy trade-off control in black-box models. Experiments demonstrate that DP-HD achieves 94.43% anomaly detection accuracy under privacy budget ε = 1—surpassing state-of-the-art methods—and exhibits markedly reduced accuracy degradation under strong noise, thus ensuring both high privacy guarantees and prediction robustness. Our core contribution is the first interpretable, tunable paradigm for co-optimizing privacy and performance in industrial ML applications.

Technology Category

• Machine Learning: Privacy
• Humans and AI: Human-in-the-loop Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Machine Learning (ML) models combined with in-situ sensing offer a powerful solution to address defect detection challenges in Additive Manufacturing (AM), yet this integration raises critical data privacy concerns, such as data leakage and sensor data compromise, potentially exposing sensitive information about part design and material composition. Differential Privacy (DP), which adds mathematically controlled noise to ML models, provides a way to balance data utility with privacy by concealing identifiable traces from sensor data. However, introducing noise into ML models, especially black-box Artificial Intelligence (AI) models, complicates the prediction of how noise impacts model accuracy. This study presents the Differential Privacy-Hyperdimensional Computing (DP-HD) framework, which leverages Explainable AI (XAI) and the vector symbolic paradigm to quantify noise effects on accuracy. By defining a Signal-to-Noise Ratio (SNR) metric, DP-HD assesses the contribution of training data relative to DP noise, allowing selection of an optimal balance between accuracy and privacy. Experimental results using high-speed melt pool data for anomaly detection in AM demonstrate that DP-HD achieves superior operational efficiency, prediction accuracy, and privacy protection. For instance, with a privacy budget set at 1, DP-HD achieves 94.43% accuracy, outperforming state-of-the-art ML models. Furthermore, DP-HD maintains high accuracy under substantial noise additions to enhance privacy, unlike current models that experience significant accuracy declines under stringent privacy constraints.

Problem

• Balancing privacy and transparency in additive manufacturing monitoring
• Quantifying noise effects on model accuracy using explainable AI
• Ensuring robust privacy protections without compromising ML performance

Innovation

• Combines Explainable AI with Hyperdimensional Computing
• Uses Signal-to-Noise Ratio to optimize privacy-accuracy
• Achieves high accuracy with robust privacy in AM