8 citations · 9 across the 2 of their papers we have counts for
3 papers
cs.CR2023
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Haomin Zhuang, Mingxian Yu, Hao Wang +3
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices. However, the decentralized learning paradigm and…
eess.IV2023★ 8 cited
A Comparison of Image Denoising Methods
Zhaoming Kong, Fangxi Deng, Haomin Zhuang +3
The advancement of imaging devices and countless images generated everyday pose an increasingly high demand on image denoising, which still remains a challenging task in terms of b…
cs.CV2023★ 1 cited
A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion
Haomin Zhuang, Yihua Zhang, Sijia Liu
Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study…