Research Interests
My research interests mainly focus on machine learning privacy and model fairness. Recently I'm working on federated leaning and privacy problems occurred in generative models (e.g., LLMs).
|
Publications
|
Sneakyprompt: Jailbreaking text-to-image generative models
Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong, and Yinzhi Cao
in the Proceedings of IEEE Symposium on Security and Privacy (SP) 2024.
Reported by MIT Technology Review and IEEE
|
EdgeMixup: Embarrassingly Simple Data Alteration to Improve Lyme Disease Lesion Segmentation and Diagnosis Fairness
Haolin Yuan*, John Aucott, Armin Hadzic, William Paul, Marcia Villegas de Flores, Philip Mathew, Philippe Burlina, and Yinzhi Cao
in the Proceedings of th 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023
|
PrivateFL: Accurate, Differentially Private Federated Learning via Personalized Data Transformation
Haolin Yuan, Yuchen Yang*, Bo Hui*, Neil Gong, and Yinzhi Cao *:equally contributed
in the Proceedings of USENIX Security Symposium, 2023.
|
Fortifying Federated Learning against Membership Inference Attacks via Client-level Input Perturbation
Yuchen Yang, Haolin Yuan, Bo Hui, Neil Gong, Neil Fendley, Philippe Burlina, and Yinzhi Cao
to appear in the Annual IEEE/IFIP International Conference on Dependable Systems and Network (DSN), 2023.
|
ImageAlly: A Human-AI Hybrid Approach to Support Blind People in Detecting and Redacting Private
Image Content
Zhuohao Zhang, Smirity Kaushik, JooYoung Seo, Haolin Yuan, Sauvik Das, Leah Findlater, Danna Gurari, Abigale Stangl, Yang Wang
in the Proceedings of the 19th Symposium on Usable Privacy and Security (SOUPS), 2023
|
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Haolin Yuan*, Bo Hui*, Yuchen Yang*, Philippe Burlina, Neil Zhenqiang Gong, and Yinzhi Cao *:equally contributed
in the Proceedings of European Conference on Computer Vision (ECCV), 2022.
|
Practical Blind Membership Inference Attack via Differential Comparisons
Bo Hui*, Yuchen Yang*, Haolin Yuan*, Philippe Burlina, Neil Gong, Yinzhi Cao *:equally contributed
in the Proceedings of Network & Distributed System Security Symposium (NDSS), 2021
|
WebAlly - A case study of Web-task friend sourcing in solving CAPTCHA
Zhuohao Zhang, Zhilin Zhang, Haolin Yuan, Nata M Barbosa, Sauvik Das, Yang Wang
in the Proceedings of Symposium on Usable Privacy and Security (SOUPS), 2021
|
Teachning/Researching Experience
Teaching Asssitant | Brandeis University
Course: Precalculus Mathematics
Course Assistant | Johns Hopkins University
Course: Web Security
Research Assistant | Johns Hopkins University
Date: Mar 2020 - present
|
|