Huadi Zheng

Protecting Decision Boundary of Machine Learning Model With Differentially Private Perturbation

2020 · IEEE Transactions on Dependable and Secure Computing

Machine learning service API allows model owners to monetize proprietary models by offering prediction services to third-party users. However, existing literature shows that model parameters are vulnerable to extraction attacks which accumulate prediction queries and …

An extraction attack on image recognition model using VAE-kdtree model

2021

This paper proposes a black box extraction attack model on pre-trained image classifiers to rebuild a functionally equivalent model with high similarity. Common model extraction attacks use a large number of training samples to feed …

SpMis: An Investigation of Synthetic Spoken Misinformation Detection

2024 · arXiv (Cornell University)

In recent years, speech generation technology has advanced rapidly, fueled by generative models and large-scale training techniques. While these developments have enabled the production of high-quality synthetic speech, they have also raised concerns about the …