Wei Ma

Wei Ma

A Coder, A Researcher, A Scientist

中文

Wei Ma, Ph.D.

I am an Associate Senior Lecturer (Tenure Track) in Software Engineering at Blekinge Institute of Technology (BTH), Sweden, and an ELLIIT faculty member. ELLIIT is Sweden’s national strategic research environment in IT and mobile communications. My research lies at the intersection of AI for Software Engineering and cybersecurity, focused on the trustworthiness of software when large language models participate in its development and operation.

My first-author paper Test Selection for Deep Learning Systems received the ACM TOSEM Outstanding Paper Award in 5 Years (2026) — one paper selected from all those published in the journal across five years. Other awards include Best Paper at ICSE 2025 Industry Track, Best Paper at ML4CS 2025, and an IEEE Computer Society TCSE Distinguished Paper Award at ICSME 2020. My work has been cited 1,700+ times (h-index 19) and appears in ICSE, FSE, ISSTA, ASE, TOSEM, TSE, TIFS, EMSE, and IJCAI — including two papers at ICSE 2026.

I build practical systems. MazeBreaker breaks LLM safety defenses with multi-agent reinforcement learning. AgentGuard hunts package-confusion supply-chain attacks in the wild. CKGFuzzer turns code knowledge graphs into production-ready fuzz drivers and won an industry best-paper award. My LLM-based smart-contract auditor has found real vulnerabilities in deployed DeFi protocols. This work spans program analysis, AI-driven software security, smart-contract auditing and DeFi governance, large-scale fuzzing and vulnerability detection, and mutation testing for trustworthy AI.

I earned my Ph.D. at the University of Luxembourg under Prof. Yves Le Traon and Prof. Mike Papadakis. I then spent four years in Singapore’s software-security research groups — as a Research Scientist at SMU with Prof. Lingxiao Jiang, and as a Research Fellow at NTU with Prof. Yang Liu and Prof. Yi Li. I serve as an Associate Editor of Automated Software Engineering and on the ACM TOSEM Review Committee.

I am always open to strong collaborators and motivated students. Reach me at weima93@gmail.com.

News

  • Our paper, ProCURE: Addressing the Programming Concept Understanding Gap for Code Generation in LLMs via Concept-Aware Consistency Learning, has been accepted by IJCAI 2026.
  • Our paper, LIMR: Intent-Aware Mashup API Recommendation via LLM-Augmented Multi-Scale Fusion, was accepted by TSC.
  • One paper, Towards secure program partitioning for smart contracts with LLMs in-context learning, accepted by TSE.
  • I am invited as an APSEC 2026 PC member.
  • I am invited as an MSR 2027 PC member.
  • I am invited as an ICSE 2027 PC member.
  • My work, Test Selection for Deep Learning Systems, won the ACM TOSEM 2026 Outstanding Paper Award in 5 years.
  • Our work, AgentGuard, received the Best Paper Award at the 7th International Conference on Machine Learning for Cyber Security (ML4CS 2025).
  • One paper is accepted by SANER 2026.
  • Our paper, Runtime Verification of Tactical Data Link, received a Best Paper nomination at the ISSRE 2025 Industry Track.
  • I have joined the ACM TOSEM review committee.
  • Our paper, Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios, has been accepted by ICSE 2026.
  • Our paper, Detecting DeFi Fraud with a Graph-Transformer Language Model has been accepted by IEEE Transactions on Information Forensics and Security (TIFS).
  • Our paper, MazeBreaker: Multi-Agent Reinforcement Learning for Dynamic Jailbreaking of LLM Security Defenses has been accepted by ICSE 2026.

Research Interests

🔒 Cybersecurity Focus

  • Software Security & Vulnerability Detection: Advanced techniques for identifying and mitigating security vulnerabilities in software systems
  • Web3 & Blockchain Security: Smart-contract auditing, DeFi governance analysis, and decentralized system security
  • AI-Driven Security: Leveraging machine learning for automated security analysis and threat detection
  • Code Model Security: Adversarial attacks and defenses for large language models in software engineering

🔧 Software Engineering Excellence

  • Software Testing: Mutation testing, fuzz testing, and comprehensive quality assurance methodologies
  • Trustworthy AI: Robustness evaluation, interpretability analysis, and reliable AI system deployment
  • Code Intelligence: Syntax-semantic modeling and controllability analysis of code foundation models
  • Program Analysis: Static and dynamic analysis techniques for software understanding and verification

Security Highlights

  • 🏆 Awards & Recognition: ACM TOSEM 2026 Outstanding Paper Award in 5 Years; ML4CS 2025 Best Paper Award; ICSE 2025 Industry Track Best Paper Award; ICSME 2020 Distinguished Paper Award
  • 🔍 Audit & Governance: Explainable findings and auditor workflows for smart-contract security; Large-scale empirical study across major DeFi applications
  • 🛡️ Industry Transfer: Code knowledge-graph fuzzing and root-cause analysis
  • 🤖 MazeBreaker: Multi-agent RL for dynamic jailbreaking of LLM defenses (ICSE 2026)
  • ⚡ LLM for Security: Attacking and hardening code models; secure software supply chain; trustworthy/robust AI for code & systems

Academic Appointments

  • Associate Senior Lecturer (Tenure Track), Blekinge Institute of Technology (BTH), Sweden (May 2026 – Present)
  • Research Scientist, Singapore Management University (Oct. 2024 – May 2026)
  • Research Fellow, Nanyang Technological University (Oct. 2022 – Oct. 2024)
  • Research Assistant, University of Luxembourg (May 2022 – Sep. 2023)

Academic Service

  • Associate Editor, Automated Software Engineering (Springer)
  • Review Committee, ACM TOSEM
  • Program Committee: ICSE 2027, MSR 2027, APSEC 2026, ISSTA 2024
  • Reviewer: TOSEM, TSE, EMSE, JSS, JSA, KNOSYS, ASE NIER

Publications

Selected work is listed on the publications page; see my Google Scholar profile for the complete list.