A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics
It addresses privacy and security risks in Industry 4.0 robotics for researchers and practitioners, but is incremental as a survey without new empirical results.
This paper surveys privacy attacks targeting AI-robotics systems integrated with Digital Twin technologies, discussing data leakage and model exfiltration risks, and advocates for trusted autonomy with ethical frameworks to enhance security.
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.