A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics

TL;DR

This survey reviews privacy attack methods on AI-enabled digital twin robotic systems, highlighting vulnerabilities, potential data leaks, and the importance of ethical safeguards for secure, trustworthy Industry 4.0 robotics.

Contribution

It provides a comprehensive overview of privacy threats in AI and digital twin robotics, emphasizing design considerations and advocating for trusted autonomy frameworks.

Findings

Exfiltration and data leakage of ML models are significant risks.

Physics-based models can also be targeted for extraction.

Robust ethical frameworks are essential for secure AI robotics.

Abstract

Industry 4.0 has witnessed the rise of complex robots fueled by the integration of Artificial Intelligence/Machine Learning (AI/ML) and Digital Twin (DT) technologies. While these technologies offer numerous benefits, they also introduce potential privacy and security risks. This paper surveys privacy attacks targeting robots enabled by AI and DT models. Exfiltration and data leakage of ML models are discussed in addition to the potential extraction of models derived from first-principles (e.g., physics-based). We also discuss design considerations with DT-integrated robotics touching on the impact of ML model training, responsible AI and DT safeguards, data governance and ethical considerations on the effectiveness of these attacks. We advocate for a trusted autonomy approach, emphasizing the need to combine robotics, AI, and DT technologies with robust ethical frameworks and trustworthiness principles for secure and reliable AI robotic systems.