Privacy in Quantum Machine Learning
Tutorial ContentATISPRICAI

Privacy in Quantum Machine Learning Tutorial Series

Quantum machine learning (QML) has attracted increasing interest as quantum computing advances toward practical learning and data-processing applications. At the same time, the use of sensitive data in quantum learning systems raises important privacy and security concerns, motivating the development of privacy-preserving techniques specifically designed for QML.

These tutorials introduce the foundations of quantum computing and QML from a privacy perspective, followed by an in-depth discussion of emerging topics in privacy-preserving quantum machine learning. We will cover representative privacy mechanisms, privacy risks and attacks, quantum differential privacy, privacy auditing, and distributed settings such as quantum federated learning (QFL). We will also discuss their connections to classical privacy-preserving machine learning and highlight key theoretical and practical challenges.

The tutorial is intended to provide researchers and practitioners with a structured understanding of privacy in QML, while identifying open challenges and promising directions for future research.

Main Presenters
Baobao Song

Baobao Song is a PhD student at the University of Technology Sydney. Her research interests include quantum computation, differential privacy, and smart tourism.

Dr. Shiva Pokhrel

Shiva Raj Pokhrel is a distinguished Marie Curie Fellow, Senior IEEE Member, and Research Leader at Deakin University. He is also a Senior Lecturer at the School of IT, Deakin University, Australia. With a PhD in ICT Engineering, Dr. Pokhrel brings a wealth of expertise in experimental distributed quantum computing, communication, and large-scale quantum experiments. His career spans roles as a Research Fellow at the University of Melbourne and a seven-year tenure as a System Engineer, solidifying his foundation in both theoretical and applied research. Dr. Pokhrel is a leader in mobile computing, quantum technologies, and distributed quantum and quantum machine learning systems.

Prof. Gang Li

Prof. Gang Li is currently a Professor at the School of IT, Deakin University, Australia. He is an internationally recognized expert in data mining and business intelligence. He has supervised and co-supervised 18 PhD students to completion, and published over 200 papers in the project area, with Google scholar citations of 6,000+ and an h-index of 35. CI Li holds one international patent and has substantial research experience in graphical models and privacy-aware data science. Her proposed preference model method won the IEEE/ACM ASONAM 2012 Best Paper Award, and his series work on trajectory analysis won the IFITT award for Journal Paper of the Year (2015 and 2017). He has developed a mechanism for privacy preservation that retrieves user rating information while retaining anonymity in product and tag recommendation systems. We have also investigated information loss in coupled datasets and proposed an improved differential privacy mechanism to accommodate coupled datasets. These works have been presented at prestigious conferences and published in journals, including IEEE Transactions on Information Forensics and Security, and IEEE Transactions on Data and Knowledge Engineering, and have won the best student award at PAKDD. He is an associate editor for Decision Support Systems (Elsevier), the Journal of Information & Knowledge Management (World Scientific) and Cyber Security (Springer).

Key References

• Song, B., Pokhrel, S. R., Vasilakos, A. V., Zhu, T., & Li, G.(2025). Toward a hybrid quantum differential privacy. IEEE Journal on Selected Areas in Communications, 43(8), 2890–2897.

• Song, B., Pokhrel, S. R., Vasilakos, A. V., Zhu, T., & Li, G. (2026). Quantum-KIP: Kernel Inducing Points for Quantum Privacy. IEEE Transactions on Information Forensics and Security.

• Gurung, D., & Pokhrel, S. R. (2026). LLM-QFL: Distilling large language model for quantum federated learning. IEEE Transactions on Network and Service Management.

• Pokhrel, S. R. (2026). Quantum Position Navigation Timing for Autonomous Vehicles: A Federated Learning Framework. IEEE Transactions on Vehicular Technology.

• Gurung, D., Pokhrel, S. R., & Li, G. (2025). Quantum federated learning for metaverse: Analysis, design, and implementation. IEEE Transactions on Network and Service Management, 22(3), 2595–2606.