Welcome to the InspiringGroup


The InspiringGroup is a dynamic research group here @ Tsinghua University INSC. We have worked on a wide range of topics centering around data. We build secure and efficient underlying systems infrastructure to support data transmissions and computations. Meanwhile, we create various data-centric applications with special interests on data security and privacy. See our Research for more details.

The InspiringGroup is led by Principal Investigator (PI), Dr. Zhuotao Liu, who has a strong track-record in both academia and industry. Dr. Liu received his Ph.D. from University of Illinois at Urbana-Champaign (UIUC) and worked at Google as a Technical Lead in both the NetInfra (Network Infrastructure) and GGN (Google Global Networking) team.

We are looking for new Ph.D. students, Postdocs, Master students, undergraduate students and external interns to join our team. Here at InspiringGroup, we strive to build a friendly, supportive, and flourishing culture, and to make your experiences at InspiringGroup full of “Wow Moments”. See Future Students.

News

April 2024

[Privacy Computing for AI] Our paper on training graph nerual networks (GNNs) over distributed and private graph data across multiple data providers is accepted by ACM CCS 2024. This work features multiple novel crypto constructions to realize fully-distributed and scalable GNN training/inference over distributed private graph data.

Feb 2024

[Privacy Theory in ML] Our paper on understanding the data privacy in FL is accepted by USENIX Secuirty 2024.

Jan 2024

[Network Security] Our paper on detecting and interpreting BGP anomalies at scale is accepted by USENIX Secuirty 2024.

Dec 2023

[Academic Services] Invited to serve on the TPC of ACM CCS 2024 (Machine Learning Security Track), Usenix Security 2024, SIGMETRICS 2024 and IEEE ICDCS 2024. Please consider to submit.

Dec 2023

[ML Systems] Our paper on intelligent network dataplane (INDP) is accepted by USENIX NSDI 2024, This work features the most advanced IDNP design that enables nerual network driven traffic analysis at line-speed.

Sep 2023

[Privacy Computing for AI] Our paper on privacy-preserving machine learning is accepted by NDSS 2024. This work features multiple novel cryptography constructions to accelerate AI training / inference over encrypted data.

Sep 2023

[Web Security] Our paper on zero-day Web attack detection is accepted by ACM CCS 2023.

August 2023

[Data & Privacy Computing] Our paper on building a utility-driven data marketplace is accepted by ACM CCS 2023. This work features a robust and verifiable Federated Learning architecture, underpinned by a secure model evaluation protocol to remove malicious model updates and a zero-knowledge proving system that ensures fair data trading.

August 2023

[Network Security] Our paper on Intelligent Network Data Plane wins the USENIX Security 2023 Distinguished Paper Award!

... see all News