Yi Liu
Short Bio
He received the B.Eng degree from the Heilongjiang University, China in 2019 (Early Graduation Base On Academic Excellence).
News
Education
B.E., School of Data Science and Technology, Heilongjiang University, Harbin, China, Aug. 2016 - Sept. 2019 (Early Graduation Base On Academic Excellence).
Research Interests
Privacy and Security (AI security, federated learning, and machine unlearning)
Edge AI and Computing (federated learning, communication-efficient edge learning)
Data Science and AI (data pricing, high-dimensional estimation, and learning to optimize)
Wireless Communications and Networking (5G and beyond, AIoT)
Selected Publications
Privacy and Security
[INFOCOM’22] Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li, “The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining”, in Proc. of INFOCOM, 2022.
[KDD’24] Yi Liu, Cong Wang, and Xingliang Yuan, “BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning”, in Proc. of KDD, 2024.
[ACM MM’24] Yi Liu, Chengjun Cai, Xiaoli Zhang, Xingliang Yuan, and Cong Wang, “Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts”, in Proc. of ACM MM, 2024.
Federated Learning
[IEEE IoTJ] Yi Liu, Sahil Garg, Jiangtian Nie, Yang Zhang, Zehui Xiong, Jiawen Kang, and M. Shamim Hossain, “Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach,” in IEEE Internet of Things Journal, vol. 8, no. 8, pp. 6348-6358, 15 April, 2021. (IEEE ComSoc Outstanding Paper Award)
[IEEE IoTJ] Yi Liu, James J.Q.Yu, Jiawen Kang, Dusit Niyato, and Shuyu Zhang, “Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach,” in IEEE Internet of Things Journal, vol. 7, no. 8, pp. 7751-7763, Aug. 2020. (Second Prize of Guangdong Computer Federation Outstanding Research Paper Award)
Some Useful Links
|