Trust-native AI
Secure Transformer inference, private collaborative learning, secure graph computation, and verifiable federated learning.
Zhuotao Liu
Associate Professor
Institute for Network Sciences and Cyberspace
Tsinghua University
Researcher in trustworthy AI, secure networked systems, and intelligent network infrastructure. Since joining Tsinghua in 2021, Dr. Liu has built an independent research program spanning trust-native AI, privacy-preserving computation, robust learning-based security, programmable data planes, and secure Internet infrastructure. This work combines fundamental algorithms with deployable systems and has earned three Distinguished Paper Awards at USENIX Security (2023 and 2024) and ACM CCS (2025), as well as the Internet Defense Prize at USENIX Security 2024. Before joining Tsinghua, he led network-infrastructure projects at Google and received two Google Feats of Engineering Awards during his four years there. He earned his Ph.D. in Computer Engineering from the University of Illinois Urbana-Champaign (UIUC) in 2017, and part of his research there won the NSF I-Corps award.
Our work on trust-native AI inference infrastructure using legacy GPUs was accepted to ACM CCS 2026.
Our work on meta-learning for continual traffic analysis was accepted to USENIX Security 2026.
RingSG received a Distinguished Paper Award at ACM CCS 2025.
Our paper on confidential/private inference over Transformer-based large models via novel cryptography constructions is accepted by IEEE S&P 2026.
Another three papers on RL-driven traffic analysis, website fingerprinting, and web application firewall are accepted by ISOC NDSS 2026.
Our paper on understanding BGP hijacking attacks given partially deployed ROV is accepted by ISOC NDSS 2026.
02
Research
Robust Learning for Network Security
Traffic analysis, website fingerprinting, and routing anomaly detection that remain effective under changing conditions and adversarial manipulation.
Intelligent Network Infrastructure
Machine learning in programmable network devices, high-performance datacenter networks, and network lifecycle automation.
Deployable and Secure Internet Systems
Practical defenses for Internet routing and DDoS attacks, alongside secure network control and cross-chain interoperability.
Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection
CertTA: Certified Robustness Made Practical for Learning-Based Traffic Analysis
RingSG: Optimal Secure Vertex-Centric Computation for Collaborative Graph Processing
Brain-on-Switch: Towards Advanced Intelligent Network Dataplane via NN-Driven Traffic Analysis at Line-Speed
CoGNN: Towards Secure and Efficient Collaborative Graph Learning
Learning with Semantics: Towards a Semantics-Aware Routing Anomaly Detection System
Pencil: Private and Extensible Collaborative Learning without Non-Colluding Assumption
An Efficient Design of Intelligent Network Data Plane
iSyn: Semi-Automated Smart Contract Synthesis from Legal Financial Agreements
martFL: Enabling Utility-Driven Data Marketplace with a Robust and Verifiable Federated Learning Architecture
HyperService: Interoperability and Programmability Across Heterogeneous Blockchains
04
Awards & Recognition
- 2026
Outstanding Doctoral Dissertation Advisor（清华大学优秀博士学位论文指导教师）
Tsinghua University
- 2025
Teaching Award, Chinese Institute of Electronics
An innovative cybersecurity course
- 2025
Distinguished Paper Award · ACM CCS
Secure and optimal multi-party graph processing
- 2025
Scientific and Technological Progress Award, Chinese Institute of Electronics
Trustworthy multi-party computations for Internet-scale systems and applications
- 2024
Distinguished Paper Award · USENIX Security
Secure Internet routing
- 2024
Internet Defense Prize · USENIX Security
Secure Internet routing
- 2023
Distinguished Paper Award · USENIX Security
On-chip AI for networking
- 2020
Google Feats of Engineering Award
Automated datacenter network management and capacity augmentation
- 2019
Google Feats of Engineering Award
Scalable datacenter control plane and network availability
- 2018
Best-in-session Presentation Award · IEEE INFOCOM
Datacenter networking
- 2017
NSF I-Corps Award
Network security and DDoS prevention
05
Academic Service
Editorial Service
- 2025–present
Associate Editor
IEEE Transactions on Dependable and Secure Computing (TDSC)
Program Committees
- 2027
IEEE S&P; USENIX Security
- 2026
IEEE S&P; ACM CCS; USENIX Security
- 2025
ACM CCS; ACM SIGMETRICS/Performance
- 2024
ACM CCS; USENIX Security; IEEE ICDCS
- 2022–2023
ACM CCS (2022, 2023); IEEE ICDCS (2023)
My first Ph.D. graduate, Zhenhua Zou, received Tsinghua University’s Outstanding Doctoral Dissertation Award in 2026. He also first-authored RingSG, which received the ACM CCS 2025 Distinguished Paper Award.
- 2023–present
Introduction to Cybersecurity
Undergraduate · Co-instructor
- 2022–present
Applied Cryptography and Blockchain
Graduate · Primary instructor
- 2022–present
Data Security
Graduate · Co-instructor
- 2022–present
Advanced Internet Architecture
Graduate · Guest lecturer
07
Work With Us
I welcome students and collaborators interested in secure networking, systems, and trustworthy AI.
Join InspiringGroup →