Contact
Websites
Biography
Dr. Perley Xu is a Lecturer in Computing at the School of Science and Engineering, University of Dundee, UK. She previously held positions at the University of Liverpool and Imperial College London. Dr. Xu obtained her PhD from the University of Liverpool in 2024 and holds a master’s degree in Electronic Information Engineering from Central South University, China.
Research
Research Interests
Dr. Xu’s research primarily focuses on AI safety, aiming to develop advanced frameworks that enhance the robustness and trustworthiness of AI systems, particularly in high-stakes applications such as healthcare and autonomous systems. By addressing critical safety challenges, she aspires to contribute to the responsible deployment of AI technologies in real-world scenarios. Her impressive track record includes numerous publications in leading peer-reviewed journals and conferences, such as Artificial Intelligence Review, Machine Learning, IEEE Transactions on Mobile Computing (TMC), AAAI, and ICASSP, underscoring her commitment to advancing knowledge in AI safety and related fields.
Selected Research Outputs
- Huang, X., Ruan, W., Huang, W., Jin, G., Dong, Y., Wu, C., et al. (2024). A survey of safety and trustworthiness of large language models through the lens of verification and validation. Artificial Intelligence Review, 57(7), 175.
- Chen, Z., Wang, F., Mu, R., Xu, P., Huang, X., Ruan, W. (2024). SAT: Symmetric Adversarial Training for Inherent Label Noise. Machine Learning, 113, 3589-3610.
- Xu, P., Ruan, W., Huang, X. (2022). Quantifying Safety Risks of Deep Neural Networks. Complex & Intelligent Systems, 1-18.
- Wang, F., Xu, P., Huang, X., Ruan, W. (2023). Towards Verifying the Geometric Robustness of Large-scale Neural Networks. In Proceedings of the Thirty-Seventh Conference on Artificial Intelligence (AAAI’2023), Washington, DC, USA, Feb 7-14.
- Zhang, C., Ruan, W., Xu, P. (2023). Reachability Analysis of Neural Network Control Systems. In Proceedings of the Thirty-Seventh Conference on Artificial Intelligence (AAAI’2023), Washington, DC, USA, Feb 7-14.
- Xu, P., Wang, F., Ruan, W., Zhang, C., Huang, X. (2023). SORA: Scalable Black-box Reachability Analyser on Neural Networks. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, June 4-10.
- Zhang, C., Ruan, W., Wang, F., Xu, P., Huang, X. (2023). Model-Agnostic Reachability Analysis on Deep Neural Networks. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Osaka, Japan, May 25-28.
- Ruan, W., Sheng, Q. Z., Xu, P., Yang, L., Gu, T., et al. (2018). Making Sense of Doppler Effect for Multi-Modal Hand Motion Detection. IEEE Transactions on Mobile Computing (TMC), 17(9), 2087-2100.
Teaching
Dr. Xu has extensive experience in developing and delivering teaching across a range of computer science-related topics. She is an Associate Fellow of the Higher Education Academy. Currently, she teaches:
- DI22010 - Object-Oriented Analysis and Design (OOAD)
- DI32003 - Theory of Computation
- DI40001 - Honours Project (Computing)
PhD Projects
Dr. Xu is actively seeking talented and motivated PhD students for projects related to computing, including Deep Learning, Machine Learning, Large Language Models, and Medical Image Analysis. Interested candidates are encouraged to contact her at [email protected] with a copy of their CV to discuss potential applications and practicalities, such as suitable start dates.
Additionally, Chinese students are warmly invited to apply for the CSC PhD studentship. For more information, please visit the China Scholarship Council (CSC) Programme.