About Me

I'm now an associate research fellow in the ZGC Laboratory, working with Prof. Haixin Duan.

I received my Doctoral degree in the Institute for Network Sciences and Cyberspace from Tsinghua University in 2023 and my Bachelor degree in Communication Engineering from Beijing University of Posts and Telecommunications (BUPT) in 2018.

Currently, my research studies network security and AI Security, with a particular interest in data-driven security, Cybercrime and LLM-related security.

Research Interests

LLM Security; Data-Driven Security; AI-applied Security; Cybercrime; Network Measurement

Contact Me

• Beijing ZGC Laboratory, Beijing 100084, P.R.China
• liumx [AT] mail [DOT] zgclab.edu.cn

Other Links: Github | NISL

Publications

Google Scholar

Conference (22)

• Breaking Free from Ivory Tower: Evaluating and Enhancing Real-world Chinese Underground Adversarial Jargon Detection, [S&P'26]
  * Zhifan Jiang, * Mingxuan Liu, Yue Qin, Baojun Liu
  (* are co-first authors.)
  (Acceptance rate: x%)
  

• Characterizing Iran's Phased National Internet Shutdown in 2025: A Progressive and Distributed Action, [WWW'26]
  Shibo Cui, Mingxuan Liu (Corresponding Author), Baojun Liu, Haixin Duan, Ruixuan Li, Chaoyi Lu, Jin Zhang, Zhicheng Wang and Jinghua Bai
  (Acceptance rate: x%)
  

• Unveiling the Resilience of LLM-Enhanced Search Engines Against Black-Hat SEO Manipulation, [WWW'26]
  Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu, Zixuan Zhu, Mingxuan Liu, Baojun Liu, Mi Zhang and Min Yang
  (Acceptance rate: x%)
  

• One Email, Many Faces: A Deep Dive into Identity Confusion in Email Aliases, [NDSS'26]
  Mengying Wu, Geng Hong, Jiatao Chen, Baojun Liu, Mingxuan Liu, Min Yang
  🏆 Distinguished Paper!
  (Acceptance rate: x%)
  

• Email Cloaking: Deceiving Users and Spam EmailDetectors with Invisible ITML Settings, [ESORICS'25]
  * Bingyang Guo, * Mingxuan Liu, Yihui Ma, Ruixuan Li, Fan Shi, Min Zhang, Baojun Liu, Chengxi Xu, Haixin Duan, Geng Hong, Min Yang, Qingfeng Pan
  (* are co-first authors.)
  (Acceptance rate: x%)
  Tool website: CSEMiner
  

• Beyond Exploit Scanning: A Functional Change-Driven Approach to Remote Software Version Identification, [USENIX Security'25]
  Jinsong Chen, Mengying Wu, Geng Hong, Baichao An, Mingxuan Liu, Lei Zhang, Baojun Liu, Haixin Duan, Min Yang
  (Acceptance rate: 19%)
  

• NOKEScam: Understanding and Rectifying Non-Sense Keywords Spear Scam in Search Engines, [USENIX Security'25]
  Mingxuan Liu, Yunyi Zhang, Lijie Wu, Baojun Liu, Geng Hong, Yiming Zhang, Hui Jiang, Jia Zhang, Haixin Duan, Min Zhang, Wei Guan, Fan Shi, Min Yang
  (Acceptance rate: 19%)
  Tool website: NOKEScam Website
  

• Dive into the cloud: Unveiling the (Ab)usage of Serverless Cloud Function in the Wild, [IMC'25]
  *Yijing Liu, *Mingxuan Liu, Yiming Zhang, Baojun Liu, Jia Zhang, Geng Hong, Haixin Duan, Min Yang
  (* are co-first authors.)
  (Acceptance rate: x%)
  

• Into the Dark: Unveiling Internal Site Search Abused for BlackHat SEO, [USENIX Security'24]
  Yunyi Zhang, Mingxuan Liu, Baojun Liu, Yiming Zhang, Haixin Duan, Min Zhang, Hui Jiang, Yanzhe Li, Fan Shi
  (Acceptance rate: 18.3%))
  Tool website: ISAP Checker
  

• Tickets or Privacy? Understand the Ecosystem of Chinese Ticket Grabbing Apps, [USENIX Security'24]
  Yijing Liu, Yiming Zhang, Baojun Liu, Haixin Duan, Qiang Li, Mingxuan Liu, Ruixuan Li, Jia Yao
  (Acceptance rate: 18.3%))
  

• ChatScam: Unveiling the Rising Impact of ChatGPT on Domain Name Abuse, [DSN'24]
  Mingxuan Liu, Zhenglong Jin, Jiahai Yang, Baojun Liu, Haixin Duan, Ying Liu, Ximeng Liu, Shujun Tang
  (Acceptance rate: 20.0%)
  Open-Source: Sampled ChatScam domains are publicly available on Github.
  

• Understanding the Implementation and Security Implications of Protective DNS Services, [NDSS'24]
  Mingxuan Liu, Yiming Zhang, Xiang Li, Chaoyi Lu, Baojun Liu, Haixin Duan, Xiaofeng Zheng
  (Acceptance rate: 13.0%)
  Open-Source: The methods for identifying Protective DNS and some anonymized measurement results are publicly available on Github.
  APNIC post: Exploring the implementation and security implications of Protective DNS.
  

• Under the Dark: A Systematical Study of Stealthy Mining Pools (Ab)use in the Wild, [CCS'23]
  *Zhenrui Zhang, *Geng Hong, Xiang Li, Zhuoqun Fu, Jia Zhang, Mingxuan Liu, Chuhan Wang, Jianjun Chen, Baojun Liu, Haixin Duan, Chao Zhang, Min Yang
  (* are co-first authors.)
  (Acceptance rate: 19.15%)

• Exploring the Characteristics and Security Risks of Emerging Emoji Domain Names, [ESORICS'22]
  Mingxuan Liu, Yiming Zhang, Baojun Liu, Haixin Duan
  (Acceptance rate: 18.5%)

• Encrypted Malware Traffic Detection via Graph-based Network Analysis, [RAID'22]
  Zhuoqun Fu, Mingxuan Liu, Yue Qin, Jia Zhang, Yuan Zou, Qilei Yin, Qi Li, Haixin Duan
  (Acceptance rate: 25%)

• Ethics in Security Research: Visions, Reality, and Paths Forward, [EthiCS'22]
  Yiming Zhang, Mingxuan Liu, Mingming Zhang, Chaoyi Lu, Haixin Duan
  🏆 Best Student Paper!
  

• ValCAT: Generating Variable-Length Contextualized Adversarial Transformations using Encoder-Decode, [NAACL'22]
  Chuyun Deng, Mingxuan Liu, Yue Qin, Jia Zhang, Haixin Duan, Donghong Sun
  (Acceptance rate: 26%)

• Detecting and Characterizing SMS Spearphising Attacks, [ACSAC'21]
  Mingxuan Liu, Yiming Zhang, Baojun Liu, Zhou Li, Haixin Duan, Donghong Sun
  (Acceptance rate: 24.5%)

• Argot: Generating Adversarial Readable Chinese Texts, [IJCAI'20]
  *Zihan Zhang, *Mingxuan Liu, Chao Zhang, Yiming Zhang, Zhou Li, Qi Li, Haixin Duan and Donghong Sun
  (* are co-first authors.)
  (Acceptance rate: 12.6%)

• Lies in the Air: Characterizing Fake-base-station Spam Ecosystem in China, [ACM CCS'20]
  Yiming Zhang, Baojun Liu, Chaoyi Lu, Zhou Li, Haixin Duan, Shuang Hao, Mingxuan Liu, Ying Liu, Dong Wang and Qiang Li
  Released Dataset
  (Acceptance rate: 16.9%)

• Casino Royale: A Deep Exploration of Illegal Online Gambling, [ACSAC'19]
  Hao Yang, Kun Du, Yubao Zhang, Shuang Hao, Zhou Li, Mingxuan Liu, Haining Wang, Haixin Duan, Yazhou Shi, Xiaodong Su, Guang Liu and Zhifeng Geng
  (Acceptance rate: 22.6%)

• TL;DR Hazard: A Comprehensive Study of Levelsquatting Scams, [SecureComm'19]
  Kun Du, Hao Yang, Zhou Li, Haixin Duan, Shuang Hao, Baojun Liu, Yuxiao Ye, Mingxuan Liu, Xiaodong Su, Guang Liu, Zhifeng Geng, Zaifeng Zhang and Jinjin Liang
  (Acceptance rate: 37.6%)

Jounal (2)

• Earning in Secrecy: Understanding the Revenue-Per-Traffic Services in PCDN Network, [ENSE'26]
  Kehong Liu, Yunyi Zhang, Liu, Mingxuan Liu, Bin Wang, Xiangyu Tian, Yu Zhang

• Automatic Generation of Adversarial Readable Chinese Texts, [TDSC'22]
  Mingxuan Liu, Zihan Zhang, Chao Zhang, Yiming Zhang, Zhou Li, Qi Li, Haixin Duan and Donghong Sun

Awards

• Best Student Paper, EthiCS'22 Euro S&P
• 1st prize, Password Intelligence Guessing Competition, the 5th Qiangwangbei 2021 in Hebei
• Third prize, Stealth Challenge Competition, GeekPwn 2019 in Shanghai
• National Scholarships, Ministry of Education of China (MOE) 2015 and 2016

Services

External Reviewer

• SecureComm'23, AsiaCCS'23, TDSC'22, NDSS'22, Euro S&P'22, Esorics'21, siMLA'21, ESORICS'20

Community Service

---

Projects

• Automatic Adversarial Generation Project, [Huawei co.]
  Research on attack and defese technologies on adversarial texts

• Detection of Underground Website based on Natrual Langurage Processing (NLP), [Tsinghua]
  Completion of the website detection section based on semantic similarity comparison
  

• Detection of Malicious Traffic based on Machine Learning Technology, [Huawei co.]
  Completion of detection based on features extracted from HTTP traffic
  

• Detection of Malicious Encrypted Traffic, [Qi’anxin co.]
  Completion of detection system based on TLS flow features