Zhifeng Jiang 江志锋｜ HKUST 香港科技大学

About Me

I am a researcher at Huawei's Central Software Institute working on LLM inference efficiency and LLM-based applications. I received my PhD in 2024 from Computer Science and Engineering, Hong Kong University of Science and Technology. advised by Prof. Wei Wang. I also work closely with Dr. Ruichuan Chen and Prof. Bo Li. Prior to that, I got my Bachelor in 2019 from Department of Computer Science and Technology, Zhejiang University.

Current Topics: Natural Language Generation

Efficient Inference for LLMs:
- Decode in parallel for autoregressive LLMs
- Accelerate diffusion-based LLMs
LLM Applications: RAG and Agents:
- Domain-specific RAG-based question answering
- Hey: A general-purpose, command-line agent compatible with MCP

Topics in PhD: Privacy Preserving Machine Learning

Private Inference for LLMs:
- Protect system prompt with minimized impact on conversational quality (PromptKeeper)
- Replicate membership inference and data reconstruction attacks against LLMs (Tutorial)
Private and Efficient Federated Training:
- Secure participant selection against adversarial servers (Lotto)
- Enable dropout-resilient differential privacy with no time overhead (Dordis)
- Train asynchronously with principles for end-to-end speedup (Pisces)

Dissertation: "Towards Private and Efficient Cross-Device Federated Learning"

News

2025-08: PromptKeeper accepted to appear in the Findings of EMNLP 2025.

2024-12: One paper accepted to IEEE TDSC. Congrats to my co-authors!

2024-11: One paper accepted to ACM PPoPP 2025. Congrats to my co-authors!

2024-08: Presented our work Lotto at USENIX Security 2024.

2024-08: Given an invited talk in a seminar at Shanghai Jiao Tong University.

2024-07: Given an invited talk in an online seminar of Huawei.

2024-07: Won HKUST RedBird Academic Excellence Award.

Selected Papers

Findings of EMNLP'25 PromptKeeper: Safeguarding System Prompts for LLMs
Zhifeng Jiang, Zhihua Jin, Guoliang He

USENIX Security'24 Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning
Zhifeng Jiang, Peng Ye, Shiqi He, Wei Wang, Ruichuan Chen, Bo Li

ACM EuroSys'24 Dordis: Efficient Federated Learning with Dropout-Resilient Differential Privacy
Zhifeng Jiang, Wei Wang, Ruichuan Chen

IEEE TBD'23 Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
Zhifeng Jiang, Wei Wang, Bo Li, Qiang Yang

ACM SoCC'22 Pisces: Efficient Federated Learning via Guided Asynchronous Training
Zhifeng Jiang, Wei Wang, Baochun Li, Bo Li

Other Recent Papers

IEEE TDSC'25 Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
Peng Ye, Zhifeng Jiang, Wei Wang, Bo Li, Baochun Li

html

code

bibtex

ACM PPoPP'25 SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs
Yongkang Zhang, Haoxuan Yu, Chenxia Han, Cheng Wang, Baotong Lu, Yunzhe Li, Zhifeng Jiang, Yang Li, Xiaowen Chu, Huaicheng Li

html

bibtex

ICPP'24 FedCA: Eﬀicient Federated Learning with Client Autonomy
Na Lv, Zhi Shen, Chen Chen, Zhifeng Jiang, Jiayi Zhang, Quan Chen, Minyi Guo

html

bibtex

IEEE ICDCS'21 Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning
Minchen Yu, Zhifeng Jiang, Hok Chun Ng, Wei Wang, Ruichuan Chen, Bo Li

Best Paper Runner-Up Award

arXiv'21 FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
Zhifeng Jiang, Wei Wang, Yang Liu

preprint

code

Awards & Grants

RedBird Academic Excellence Award (HKUST, 2024, 2023)

Best Paper Runner-Up Award (IEEE ICDCS, 2021)

Outstanding Graduate (Zhejiang Province, 2019)

He Zhijun Scholarship (Dept. of CS, ZJU, 2017)

National Scholarship (Ministry of Education, China, 2017)

Professional Service

Journal Reviewer: IEEE Transactions on Mobile Computing, IEEE Transactions on Big Data, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Computers

Shadow Program Committee: ACM EuroSys 2023

Artifact Evaluation Committee: USENIX OSDI 2022, USENIX ATC 2022, ACM SOSP 2021

Journal Sub-Reviewer: IEEE Transactions on Network Science and Engineering, IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Big Data

Conference Sub-Reviewer: IEEE INFOCOM 2020-2024, IEEE ICDCS 2024, 2023 and 2021, IEEE/ACM IWQoS 2020-2021, IEEE WoWMoM 2021, IEEE ICNP 2020

Teaching

HKUST COMP3511: Operating System. (Fall 2022, Fall 2020)

HKUST COMP4651: Cloud Computing. (Fall 2021)

HKUST COMP4521: Mobile Application Development. (Spring 2020)

ZJU: Operating System (Educational Reform Class). (Fall 2018)