Ms Nianyun Song
Expertise
My research focuses on AI security and privacy, including privacy-preserving machine learning, secure neural network inference, trustworthy AI, and efficient secure computation for cloud-based AI services.
Current positions
Visiting Research Associate
School of Computer Science
Contact
Press and media
Many of our academics speak to the media as experts in their field of research. If you are a journalist, please contact the University’s Media and PR Team:
Biography
I am a Visiting Research Associate at the University of Bristol and a PhD researcher at Beijing Normal University. My research focuses on AI security and privacy, with particular interests in privacy-preserving machine learning, secure neural network inference, trustworthy AI, and secure multi-party computation.
My work explores how cryptographic and system-level techniques can protect sensitive data and models in cloud-based AI services while maintaining practical efficiency. I have worked on secure inference, model privacy, privacy-preserving verification, and efficient deployment of deep learning models under different security settings.
My work explores how cryptographic and system-level techniques can protect sensitive data and models in cloud-based AI services while maintaining practical efficiency. I have worked on secure inference, model privacy, privacy-preserving verification, and efficient deployment of deep learning models under different security settings.
Publications
Recent publications
02/09/2026Privacy-Preserving Robustness Verification for Neural Networks: 42nd Conference on Uncertainty in Artificial Intelligence
UAI '26: Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence
