About Me

I am a Ph.D. candidate in Computer Science at the University of Massachusetts Lowell (UML), under the supervision of Dr. Yimin Chen. Before joining UML, I worked as a full-time Research Assistant at Southern University of Science and Technology (SUSTech), advised by Dr. Yinqian Zhang.

I am delighted to share that I am preparing to graduate soon and am actively seeking research or academic positions. I look forward to connecting with fellow researchers, academics, and potential collaborators or employers.

Research Interests
  • Trustworthy ML — Federated Learning, Model Merging
  • LLM Security — RAG, Agent
  • Blockchain, Real-World Assets (RWA)
  • Industrial AI
Education

  • Ph.D. in CS, 2022-Now

    The University of Massachusetts Lowell, USA

  • MSc in CS, 2018-2021

    Guangzhou University, China

  • BSc in EE, 2014-2018

    Shanghai University, China

Publications

Xingyu Lyu, Mengya Zhang, Xiaokuan Zhang, Jianyu Niu, Yinqian Zhang, Zhiqiang Lin (2022). An Empirical Study on Ethereum Private Transactions and the Security Implications.

PDF

Xingyu Lyu, Shixiong Li, Ning Wang, Tao Li, Danjue Chen, Yimin Chen (2024). Adversarial Attacks on Federated Learning Revisited: a Client-Selection Perspective. IEEE Conference on Communications and Network Security (CNS).

PDF

Mengya Zhang, Xingyu Lyu, Jianyu Niu, Xiaokuan Zhang, Yinqian Zhang, Zhiqiang Lin (2024). Breaking the Privacy Barrier: On the Feasibility of Reorganization Attacks on Ethereum Private Transactions. Annual Computer Security Applications Conference (ACSAC).

PDF

Shixiong Li, Xingyu Lyu, Ning Wang, Tao Li, Danjue Chen, Yimin Chen (2025). Beyond Uniformity: Robust Backdoor Attacks on Deep Neural Networks with Trigger Selection. Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD).

PDF

Zhengyuan Jiang, Xingyu Lyu, Shanghao Shi, Yang Xiao, Yimin Chen, Thomas Hou, Wenjing Lou, Ning Wang (2025). BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning. 28th European Conference on Artificial Intelligence (ECAI).
Xingyu Lyu, Ning Wang, Yang Xiao, Shixiong Li, Tao Li, Danjue Chen, Yimin Chen (2025). Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-IIDs via Buffering. IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom).

Awards

2024 ACSAC Student Travel Grant
2024
UML Graduate Research Grant Award
2025
UMass Professional Development Fund — Graduate Research Grant
2025
Moloney Scholarship
2025

Patents

A detection method, terminal and storage medium for Ethereum private transactions
Patent No.: CN115187250B  •  Country: China  •  Year: 2022
Inventors: Yinqian Zhang, Xingyu Lyu, Jianyu Niu
A real-time detection method, terminal and storage medium for Ethereum smart contract vulnerabilities
Patent No.: CN115174279B  •  Country: China  •  Year: 2022
Inventors: Yinqian Zhang, Xingyu Lyu, Jianyu Niu

Experience

 
 
 
 
 
Research Assistant (Full-time), Security & Privacy in AI
University of Massachusetts Lowell — Advisor: Prof. Yimin Chen
September 2022 – Lowell, MA, USA
Security & privacy in ML: adversarial attacks & defenses in FL, RAG, and LLMs.
 
 
 
 
 
Visiting Student
Zhejiang Univ.
September 2025 – December 2025 Hangzhou, China
Robust Model Merging.
 
 
 
 
 
Research intern
Dewave Ventures
September 2025 – December 2025 Shanghai, China
RWA and blockchain.
 
 
 
 
 
Research engineer
Heurist.AI
June 2024 – August 2024 New York, USA
DeFi/MEV security research.
 
 
 
 
 
Visiting Student, LLM Security
HKUST (Guangzhou) — Mentor: Prof. Xinlei He
May 2024 – June 2024 Guangzhou, China
Privacy attacks on RAG; evaluation and mitigation in agent systems.
 
 
 
 
 
Research Assistant (Full-time), Blockchain Security
Southern University of Science and Technology — Advisor: Prof. Yinqian Zhang
July 2021 – August 2022 Shenzhen, China
Smart contract vulnerability detection; DeFi/MEV security research.
 
 
 
 
 
Visiting Student, Adversarial Attacks in Autonomous Vehicles
City University of Hong Kong — Advisor: Prof. Jianping Wang
December 2020 – April 2021 Hong Kong, China
Sensor attack detection and resilience in autonomous driving systems.
 
 
 
 
 
Visiting Student, Cybersecurity Range Project
Pengcheng Laboratory
December 2018 – July 2020 Shenzhen, China
Blockchain security testing and simulation in cyber range environments.