Rui Duan (段锐), Ph.D., Assistant Professor.
Department of Computer Science, University of Missouri-Kansas City.
5000 Holmes St, Kansas City, Missouri, 64110.
Email: ruiduan@umkc.edu
Office: FH560c
Rui Duan (段锐), Ph.D., Assistant Professor.
Department of Computer Science, University of Missouri-Kansas City.
5000 Holmes St, Kansas City, Missouri, 64110.
Email: ruiduan@umkc.edu
Office: FH560c
Bio
Dr. Rui Duan is an Assistant Professor in the Department of Computer Science and Information Technology at the University of Missouri-Kansas City (UMKC). He leads the SAIM Lab (Secure AI & Intelligent Media) at the UMKC, focusing on trustworthy and human-centered multimedia AI. His research has been supported by the NSF, from which he received the CRII award in 2025. Dr. Duan received his Ph.D. degree from the University of South Florida advised by Dr. Zhuo Lu. His research is centered on the intersection of AI Security and Machine Learning. He has published some notable conference papers in top-tier Security and ML conferences including ACM CCS, NDSS, IEEE S&P, IEEE/CVF CVPR, and ICML. In addition to his primary focus, his research is also related to Network Security and the Internet of Things.
Lab News
Multiple Ph.D. openings are available in our group. Welcome Self-motivated students who have - strong interests in trustworthy ML & AI, IoT designing, and human-computer interaction to join us!
[Aug, 2025] Our poster on real-time speech watermarking against hidden phone call recording has been accepted to USENIX Security 2025 Posters.
[July, 2025] I’ve received the NSF CRII award. Sincere thanks to NSF for the support!
[May, 2025] Our work investigating the audio jailbreak attack on Multimodal Large Language
Models has been accepted by DSN workshop 2025.
[Dec, 2024] Our paper exploring adversarial attack on YouTube Music Copyright System has been accepted by TDSC.
[Apirl, 2024] I Received the Student Travel Grant from IEEE S&P 2024. Thanks to S&P 2024!
[Jan, 2024] I will join UMKC as an Assistant Professor in the Department of Computer Science.
[Nov, 2023] Our paper using the most limited attack knowledge to spoof commercial speaker recognition models has been accepted by NDSS 2024.
[Aug, 2023] Our work understanding the limitation of CSI authentication via machine learning is accepted by IEEE S&P 2024.
[Feb, 2023] Our paper investigating the performance of personalized Federated Learning appears to CVPR 2023.
[Aug, 2022] I Received the Student Travel Grant from CCS 2022. Thanks to CCS 2022!
[Apirl, 2022] Our work reversing the human perception model to generate the adversarial examples against YouTube Copyright Detection has been accepted by ACM CCS 2022.
Recent Publications
📄 Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
Binhao Ma, Hanqing Guo, Zhengping Jay Luo, Rui Duan.
IEEE/IFIP International Conference on Dependable Systems and Networks (DSN workshop), 2025
📄 Perception-Aware Attack against Music Copyright Detection: Impacts and Defenses
Rui Duan, Zhe Qu, Shangqing Zhao, Leah Ding, Yao Liu and Zhuo Lu.
IEEE Transactions on Dependable and Secure Computing (TDSC)
| paper
Rui Duan, Zhe Qu, Leah Ding, Yao Liu, and Zhuo Lu.
Proceedings of the 40th Annual Network and Distributed System Security Symposium (NDSS), 2024.
Zhe Qu, Rui Duan, Xiao Han, Shangqing Zhao, Yao Liu, and Zhuo Lu.
Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P), 2024.
📄 How to Prevent the Poor Performance Clients for Personalized Federated Learning?
Zhe Qu, Xingyu Li, Xiao Han, Rui Duan, Chengchao Shen, and Lixing Chen.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
📄 Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception
Rui Duan, Zhe Qu, Shangqing Zhao, Leah Ding, Yao Liu and Zhuo Lu.
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022.
📄 Generalized Federated Learning via Sharpness Aware Minimization
Zhe Qu, Xingyu Li, Rui Duan, Yao Liu, Bo Tang and Zhuo Lu.
Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
Research Highlights
[NDSS'24] Parrot-training Attack against IoT Devices
🔊Using the most limited attack knowledge to spoof commercial speaker recognition models
[CCS'22] Music Copyright Attack against YouTube
🎶Reversing the human perception model to generate the adversarial examples