Boyang Ma

Boyang Ma

马博洋

Assistant Professor, School of Computer Science and Technology, Shandong University

👤 Bio

I am currently an Assistant Professor at the School of Computer Science and Technology, Shandong University, where I am affiliated with the Institute of Intelligent Computing (IIC), led by Professor Xiuzhen Cheng (成秀珍). I received my Ph.D. degree in Cyberspace Security from Xidian University, under the supervision of Professor Jinku Li (李金库).

My research interests span computer systems security and AI security. During my doctoral studies, I specialized in ransomware detection, with a particular focus on leveraging virtualization and trusted computing technologies to develop low-level, high-assurance defense systems that operate with enhanced security guarantees.

Currently, my research expands along two major directions. On one hand, I investigate security vulnerabilities within AI systems, including security risks in emerging agentic AI infrastructures—such as privilege escalation and access control failures in Model Context Protocol (MCP) ecosystems, as well as security threats introduced by system-level autonomous agents (e.g., tools like OpenClaw). On the other hand, I explore how AI techniques can be harnessed to address and optimize solutions for traditional system security challenges. In addition, I am actively pursuing research on embodied AI security, focusing on the safety and robustness of intelligent systems that perceive and interact with the physical world.

I am always open to academic collaborations and discussions. Please feel free to reach out via email at boyangma@email.sdu.edu.cn if you would like to connect or explore potential research opportunities together.

📝 Publications

  • Zhihao Li, Kun Li, Boyang Ma, Minghui Xu, Yue Zhang and Xiuzhen Cheng. We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems. In Proceedings of the IEEE MASS Workshop on Data Security and LLM Safety in Smart Systems 2025 (DLS 2025), Chicago, USA, Oct. 2025. Link

  • Rui Jiao, Yue Zhang, Jinku Li, and Boyang Ma. SCCA: A Multi-Agent Code Security Analysis Framework for AI-Assisted Code Generation. In Proceedings of the IEEE MASS Workshop on Data Security and LLM Safety in Smart Systems 2025 (DLS 2025), Chicago, USA, Oct. 2025. Link

  • Boyang Ma, Linxuan Zhou, Chong Liao, Yajin Zhou, Jinku Li, and Jianfeng Ma. 2025. “RansomSentry: Runtime Detection of Android Ransomware With Compiler-Based Instrumentation.” IEEE Transactions on Dependable and Secure Computing (TDSC), January, 1–17. [JCR-Q1][CCF-A]. Link

  • Boyang Ma, Yilin Yang, Jinku Li, Fengwei Zhang, Wenbo Shen, Yajin Zhou, and Jianfeng Ma. 2023. “Travelling the Hypervisor and SSD: A Tag-Based Approach Against Crypto Ransomware with Fine-Grained Data Recovery.” In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS ‘23). Association for Computing Machinery, New York, NY, USA, 341–355. [CCF-A][BIG4]. Link

  • Tang, Fei, Boyang Ma, Jinku Li, Fengwei Zhang, Jipeng Su, and Jianfeng Ma. “RansomSpector: An introspection-based approach to detect crypto ransomware.” Computers & Security 97 (2020): 101997. [CCF-B]. Link