Mingyi Zhou

Mingyi Zhou Min-Yee Joh

PhD Candidate

Monash University

Biography

I am in my final (forth) year as a PhD candidate in HumaniSE lab, Monash University, Australia. I will join Beihang University as an Assistant Professor, working with Prof. Chunming Hu and Prof. Li Li. I have the privilege of being mentored by Prof Li Li, Prof John Grundy, Prof Chunyang Chen, and Dr Xiao Chen (in a sequence of the length of supervision) in PhD. I was a PhD student in Monash SMAT Lab, leading by Prof Li Li. My current research project is focused on using SE/System solutions such as program analysis to analyze and enhance the reliability of deployed machine learning (ML) systems, especially for smart mobile apps. This includes assessing the risks associated with ML systems, protecting their intellectual property, and minimizing their attacking surface. Additionally, I am exploring ways to optimize machine learning programs on mobile devices to improve inference efficiency.

Interests
  • Software Engineering for AI
  • Mobile Security
  • AI Compiler
Education
  • PhD, 2021-now

    Monash University, Australia

  • Master of Engineering

    University of Electronic Science and Technology of China (UESTC)

  • Bachelor of Engineering

    Wuhan University of Technology, China

News

🎉 Our paper “LLM for Mobile An Initial Roadmap” has been accepted by TOSEM!
Serving as a Junior PC member in MSR'25
🎉 One paper has been accepted by ASE'24!
🎉 Received the FIT PhD Supplementary Funding!
🎉 Received the Google Travel Grant (6000$)!
🎉 One paper has been accepted by the first cycle of ISSTA'24!

Slected Publications

Quickly discover relevant content from here.
(2024). DynaMO: Protecting Mobile DL Models through Coupling Obfuscated DL Operators. In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering, Research Track [ASE'24].

PDF Cite Code DOI

(2024). Model-less Is The Best Model: Generating Pure Code Implementations to Replace On-device DL Models. In Proceedings of the 33nd ACM SIGSOFT International Symposium on Software Testing and Analysis 2024, Technical Track [ISSTA'24].

PDF Cite Code DOI

(2024). Investigating White-Box Attacks for On-Device Models. In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering 2024, Research Track [ICSE'24].

PDF Cite Code DOI

(2024). Concealing Sensitive Samples against Gradient Leakage in Federated Learning. In The 38th Annual AAAI Conference on Artificial Intelligence 2024 [AAAI'24].

PDF Cite Code DOI

(2023). ModelObfuscator: Obfuscating Model Information to Protect Deployed ML-Based Systems. In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis 2023, Technical Track [ISSTA'23].

PDF Cite Code DOI

(2020). DaST: Data-free Substitute Training for Adversarial Attacks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020 [CVPR'20 Oral, Top 5%].

PDF Cite Code DOI

Professional Services

Program Committee:

  • Annual AAAI Conference on Artificial Intelligence (AAAI'25)
  • International Conference on Software Engineering (ICSE'25), Artifact Evaluation Track
  • Mining Software Repositories (MSR'25)

Reviewer:

  • ACM Computing Surveys
  • IEEE Transaction on Software Engineering
  • ACM Transaction on Software Engineering and Methodology
  • IEEE Transaction on Image Processing
  • Knowledge-Based Systems
  • Conference on Computer Vision and Pattern Recognition (CVPR'22, 23, 24, 25)
  • International Conference on Computer Vision (ICCV'23)
  • European Conference on Computer Vision (ECCV'22, 24)
  • Asian Conference on Computer Vision (ACCV'24)