Name: Mingyi Zhou
Type: User
Company: Monash University
Bio: PhD Student at Monash University.
Research interests: Responsible AI Deployment, On-device Model Optimization, Software Engineering for AI
Location: HumaniSE Lab (Formerly in SMAT Lab)
Blog: https://zhoumingyi.github.io/
Mingyi Zhou's Projects
Code for our paper "Model-less Is the Best Model: Generating Pure Code Implementations to Replace On-Device DL Models" that has been accepted by ISSTA'24
A novel data-free model stealing method based on GAN
Code for ASE2024 Paper: DynaMO: Protecting Mobile DL Models through Coupling Obfuscated DL Operators
Code for our paper "Modelobfuscator: Obfuscating Model Information to Protect Deployed ML-Based Systems" that has been published by ISSTA'23
Reverse Engineering method for On-device Models
ensor rank learning in CP decomposition via convolutional neural network