About me
Hey! I am Liwen Xu, a second year PhD student in Computer Science at the ETH Zürich 
, and a member of the Network Security (Netsec) Group, where I was fortunate to be supervised by Prof. Adrian Perrig and advised by Prof. Huayi Duan. Previously, I obtained my
master's degree from the Institute of Cyber Science and Technology at Shanghai Jiao Tong University (SJTU)
and bachelor's degree from School of Cyber Engineering, Xidian University (XDU)
.
I am currently working on multiple projects related to DNS Security and have a wide range of interests in Compter Networks, SCION and interdisciplinary areas with AI. Previously I was focusing on Threat Discovery and Correlation, Situational Awareness and Threat Intelligence.
My resume (Last update: April, 2024) can be found here. Please feel free to contact me if you wish more information.
Education
Ph.D., ETH Zürich (ETHz), Zürich, Switzerland (Aug 2024 - Present)
- Major: Computer Science
- Supervisor: Prof. Adrian Perrig
- Advisor: Prof. Huayi Duan
- Group: Network Security (Netsec) Group
M.Eng., Shanghai Jiao Tong University (SJTU, Project 985), Shanghai, China (Sep 2021 - Mar 2024)
- Major: Cyberspace Security (Exam-exempted)
- Supervisor: Prof. Jianhua Li, Institute of Cyber Science and Technology
- Laboratory: National Engineering Research Center for Information Content Analysis Technology (NERCICAT)
- Dissertation: Research on Cyber Security Threat Sensing and Intelligence Endogenization Based on Multi-source Heterogeneous Data
- GPA: 3.7/4.0
B.Eng., Xidian University (XDU, Project 211), Xi’an, Shaanxi, China (Sep 2017 - Jun 2021)
- Major: Cyberspace Security (Experimental Class)
- Supervisor: Associate Prof. Ning Zhang and Prof. Hui Li, School of Cyber Engineering
- Dissertation: A Real-time Intelligent Detection System for Malicious Network Traffic Based on Deep Learning (Outstanding Thesis Award)
- GPA: 3.9/4.0 (Ranking: 1/40)
Selected Honors and Awards
- Postgraduate Academic Scholarship of SJTU, 2023
- Postgraduate Academic Scholarship of SJTU, 2022
- The First Prize Scholarship of SJTU (Top 10% got the awards), 2021
- Outstanding Graduate of Shaanxi (Top 1% got the awards), 2021
- Outstanding Graduate of Xidian University (Top 1% got the awards), 2021
- Outstanding Thesis Award of Xidian University (Top 1% got the awards, Advised by Prof. Ning Zhang), 2021
- Special Prize of National Cryptography Technology Competition (Top 1 got the awards), 2019
- National Scholarship, China (Top 1% got the awards), 2019
- National Scholarship, China (Top 1% got the awards), 2018
Internship
CIS (Cybersecurity Intelligence System) Development, Huawei Technologies Co., Ltd. 
(Jun 2019 – Aug 2019)
- Position: Intern, Security Intelligence Development Department
- Project Focus: Addressing data consistency challenges in Huawei's Security Situation Awareness Platform due to non-idempotent data transactions in a Hadoop environment influenced by RPC characteristics and network issues.
- Key Responsibilities: Conducted a thorough analysis of data duplication issues during Kafka data consumption by HDFS through Flume and assessed the impact on system reliability.
- Solution Proposed: Devised a strategy incorporating Redis caching to mitigate data duplication by checking the uniqueness of data prior to processing, thus enforcing data consistency.
- Outcomes: The implementation of the Redis-based solution effectively reduced the occurrence of redundant data, enhancing the accuracy of the platform's offline analytical processes.
Security Component Adaptation Based on SM Algorithm, Hikvision Digital Technology Co., Ltd. 
(Jun 2020 – Aug 2020)
- Position: Intern, Cybersecurity Department
- Project Focus: Enhancing the support for Chinese National Standard (GuoMi) cryptographic algorithms in OpenSSL version 1.1.1d/g, both in direct and EVP (Envelope) modes.
- Key Responsibilities: Added GuoMi algorithm support to OpenSSL, collaborated with the department's cryptographic engine team, and performed performance testing on Hisilicon and Intel x64 platforms.
- Solution Proposed: Developed and executed performance testing for cryptographic cards from Tsinghua University and Suzhou Guoxin, and created automation scripts for OpenSSL and mbedTLS, enhancing deployment and testing efficiency.
- Outcomes: The enhancements made to OpenSSL and the Nginx server significantly raised the performance and security standards, meeting the project's objectives and contributing to Hikvision's cryptographic infrastructure.
Publications and Invited Talks
HiSec: Towards Cyber Threat Correlation and Discovery Based on Hierarchical Graph Neural Networks
Liwen Xu1, Xiang Lin1, Jianhua Li1, Bai Min2, Liejun Wang2 The 22nd IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom-2023)- 1Institute of Cyber Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, China
- 2Qianxin Threat Intelligence Center, Qianxin Technology Group Co., LTD, Beijing 100000, China
Cloud Asset Security Analysis based on Hierarchical Graph Neural Network
ZHANG Yilian1, ZHOU Diqing1, XU Liwen2, YE Tianpeng2, LIN Xiang2 Journal of Cyber Security, China- 1State Grid Shanghai Municipal Electric Power Company, Shanghai 200122, China
- 2Institute of Cyber Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, China
Personalized Lightweight Distributed Network Intrusion Detection System in Fog Computing
YE Tianpeng1, LIN Xiang1, LI Jianhua1, ZHANG Xuankai1, XU Liwen1 Chinese Journal of Network and Information Security- 1Institute of Cyber Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, China
(Talk) Localized Intelligence Production and Threat Discovery Based on Unknown Cyberattacks Discovery Using Endogenous Data
Liwen Xu The Wuhan Cybersecurity Innovation Forum, 2023, ChinaPatents
Graph Modeling Method for Security Semantics of Critical Information Infrastructure (Under Review)
- Author: XU Liwen, BAI Min1, WANG Liejun1
- Application No.: 202311433049.1
APT Detection Method Based on Hierarchical Graph Neural Network with Spatio-temporal Feature Fusion (Under Review)
- Author: XU Liwen, BAI Min1, WANG Liejun1
- Application No.: 202311517251.2
- 1Threat Intelligence Center, QI-ANXIN Technology Group Inc., Beijing 100000, China
Anomaly Detection Method for Cloud Security Based on Graph Neural Network (Under Review)
- Author: ZHANG Yilian1, LIN Xiang2, XU Liwen2, YE Tianpeng2
- Application No.: 202210956849.0
Compression Method of Deep Learning Model for Network Intrusion Detection (Under Review)
- Author: ZHANG Yilian1, LIN Xiang2, YE Tianpeng2, XU Liwen2
- Application No.: 202210956842.9
- 1State Grid Shanghai Municipal Electric Power Company, Shanghai 200122, China
- 2Institute of Cyber Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, China
Research Projects
DaLens (DNS Self-amplification Lens)
rProfiler (DNS Resolver Profiler)
Localized Intelligence Production and Threat Discovery Based on Network Endogenous Data (Sep 2022 - Oct 2023)
- Consigner: QI-ANXIN Technology Group Inc.
- Funding: National Student Innovation Funding Joint Research Program
- Dynamic Graph Modeling: Innovated a dynamic graph model for complex networks using multi-source data, significantly enhancing real-time attack detection and reducing computational overhead.
- Hierarchical Neural Network for Threat Correlation and Discovery: Created HiSec, a cutting-edge hierarchical neural network framework, improving the detection of advanced cyber threats and enriching threat intelligence.
- Attack Graph-Based Threat Intelligence: Formulated the Ag2Intel model to transform attack graphs into actionable threat intelligence, elevating the accuracy and readability of security insights.
RISC-V Processor Core for Chinese National Cryptographic Algorithm (May 2019 - Nov 2019)
- Project Overview: Achieved top honors for designing a RISC-V processor tailored to Chinese National Cryptographic Standards, specifically focusing on the structural features of the SM3 and SM4 algorithms.
- Research and Development: Conducted in-depth research into the SM3 and SM4 algorithms to identify critical areas for acceleration. Designed custom acceleration instructions within the RISC-V instruction set architecture.
- Impact: The enhanced Xcore processor facilitated accelerated cryptographic instruction execution and improved instruction speedup ratio and algorithm throughput without additional hardware investment.
Teaching
252-0064-00L Computer Networks, (Spring 2025)
- Teaching Assistant, D-INFK, ETH Zürich
263-4640-00L Network Security, (Autumn 2024/2025.)
- Teaching Assistant, D-INFK, ETH Zürich
IS412 Theory and Application of Content Security, (Sep 2021 – Jun 2023)
- Teaching Assistant, Shanghai Jiao Tong University
Supervision
Senne Mark Z Van den Broeck. Detecting and Mitigating DNS Message Amplification Attacks. Master's thesis, ETH Zürich, March 2025
- Advisors: Dr. Huayi Duan, Liwen Xu, Prof. Mathias Payer, Dr. Bernhard Tellenbach and Prof. Adrian Perrig.
Marko Lisicic. A First Look at DNS Cache Exhaustion. Master's thesis, ETH Zürich, March 2025
- Advisors: Dr. Huayi Duan, Liwen Xu, and Prof. Adrian Perrig.
Xuhao Wan. Research on Cybersecurity Threat Intelligence Model Design and Parsing and Cleaning Techniques. Bachelor's thesis (A+), SJTU, June 2023
- Advisors: Prof. Jianhua Li, Liwen Xu.
Tong Guo. Cryptocurrency Mining Behavior Detection Based on Deep Learning and Multidimensional Feature Recognition. Bachelor's thesis, SJTU, June 2023
- Advisors: Dr. Xiang Lin, Liwen Xu.
Academic Services
Reviewer
- USENIX Symposium on Networked Systems Design and Implementation (NSDI 2026, External)
- IEEE/ACM International Symposium on Quality of Service (IWQoS 2025, External)
- Asia-Pacific Workshop on Networking (APNet 2025, External)
Artifact Reviewer
- IEEE Symposium on Security and Privacy (IEEE S&P 2026, Artifact Evaluation Committee)
- USENIX Security Symposium (USENIX Security 2025, External)
Submission System Administrator
- The 33rd IEEE International Conference on Network Protocols (ICNP 2025)
Links
Hi, there! I am a master student at HITsz. Coding for fun and meeting interesting people. I will be happy if you would like to communicate with me.
Yukang Lian (廉玉康)
A normal master student at HITsz. Love opensource. Apache Doris contributor.
Hi! I am a master student at School of Artificial Intelligence, XDU. Learned something about Cyber Security and Computer Vision. I feel great when talking and working with people.
Jerry Wang (王屹晨)
A student at XDU. Majoring in Computer Vision. Working hard to code better.
I am Wei Li, an exam-exempted master’s student who majors in cyberspace security at School of Cyber Engineering, Xidian University (XDU), China.
