About

Jia Liu is an Assistant Professor of Bioengineering at Harvard John A. Paulson School of Engineering and Applied Sciences. His primary teaching area is bioengineering, and he is involved in research related to applied mathematics, computational neuroscience, modeling physical and biological phenomena, and systems. His work encompasses a broad range of interdisciplinary fields including bioinspired robotics and computing, cell and tissue engineering, biomaterials, biomechanics, motor control, and the application of artificial intelligence and machine learning to biological systems. Liu's research aims to advance understanding and development in bioengineering through innovative approaches that integrate computational methods, physical modeling, and biological insights.

Research topics

• Computer Science
• Artificial Intelligence
• Mathematics
• Archaeology
• History
• Distributed computing
• Econometrics

Selected publications

• FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

  2021 · 775 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

  Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious. The key idea of existing Byzantine-robust federated learning methods is that the service provider performs statistical analysis among the clients' local model updates and removes suspicious ones, before aggregating them to update the global model. However, malicious clients can still corrupt the global models in these methods via sending carefully crafted local model updates to the service provider. The fundamental reason is that there is no root of trust in existing federated learning methods. In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust. In particular, the service provider itself collects a clean small training dataset (called root dataset) for the learning task and the service provider maintains a model (called server model) based on it to bootstrap trust. In each iteration, the service provider first assigns a trust score to each local model update from the clients, where a local model update has a lower trust score if its direction deviates more from the direction of the server model update. Then, the service provider normalizes the magnitudes of the local model updates such that they lie in the same hyper-sphere as the server model update in the vector space. Our normalization limits the impact of malicious local model updates with large magnitudes. Finally, the service provider computes the average of the normalized local model updates weighted by their trust scores as a global model update, which is used to update the global model. Our extensive evaluations on six datasets from different domains show that our FLTrust is secure against both existing attacks and strong adaptive attacks.

  DOI

Recent grants

• CIF: Small: Taming Convergence and Delay in Stochastic Network Optimization with Hessian Information

  NSF · $201k · 2020–2022

• CAREER: Computing-Aware Network Optimization for Efficient Distributed Data Analytics at the Wireless Edge

  NSF · $110k · 2020–2021

• NeTS: Small: Toward Optimal, Efficient, and Holistic Networking Design for Massive-MIMO Wireless Networks

  NSF · $287k · 2017–2020

• NIH Grant P20GM103472

  NIH · $26.3M · 2019

• CIF: Small: Taming Convergence and Delay in Stochastic Network Optimization with Hessian Information

  NSF · $318k · 2017–2021

Frequent coauthors

• Yiying Song

  Chinese Academy of Medical Sciences & Peking Union Medical College

  104 shared

• Wei-Qiang Zhang

  Tsinghua University

  75 shared

• Zonglei Zhen

  Beijing Normal University

  72 shared

• Qiong Hu

  Ministry of Agriculture and Rural Affairs

  66 shared

• Hao Zhang

  Northeast Electric Power University

  64 shared

• Desheng Mei

  Oil Crops Research Institute

  60 shared

• Hongtao Cheng

  First Affiliated Hospital of Jinan University

  58 shared

• Xiangzhen Kong

  Zhejiang University

  56 shared

Labs

• Liu LabPI

Education

• Ph.D., Department of Brain & Cognitive Sciences

  Massachusetts Institute of Technology

Similar researchers at Harvard University

• Walter C Willetth-429
• JoAnn E Mansonh-359
• Randy L. Bucknerh-268
• Edward Giovannuccih-267
• Kristen Andersonh-263