210 citations · 431 across the 8 of their papers we have counts for
8 papers
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
Haichao Sha, Zihao Wang, Yuncheng Wu +2
Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resul…
Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
Haichao Sha, Yang Cao, Yong Liu +3
Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined no…
A Fusion-Denoising Attack on InstaHide with Data Augmentation
Xinjian Luo, Xiaokui Xiao, Yuncheng Wu +2
InstaHide is a state-of-the-art mechanism for protecting private training images, by mixing multiple private images and modifying them such that their visual features are indisting…
Serverless Data Science -- Are We There Yet? A Case Study of Model Serving
Yuncheng Wu, Tien Tuan Anh Dinh, Guoyu Hu +3
Machine learning (ML) is an important part of modern data science applications. Data scientists today have to manage the end-to-end ML life cycle that includes both model training…
Communication-efficient Decentralized Machine Learning over Heterogeneous Networks
Pan Zhou, Qian Lin, Dumitrel Loghin +3
In the last few years, distributed machine learning has been usually executed over heterogeneous networks such as a local area network within a multi-tenant cluster or a wide area…
Feature Inference Attack on Model Predictions in Vertical Federated Learning
Xinjian Luo, Yuncheng Wu, Xiaokui Xiao +1
Federated learning (FL) is an emerging paradigm for facilitating multiple organizations' data collaboration without revealing their private data to each other. Recently, vertical F…
Privacy Preserving Vertical Federated Learning for Tree-based Models
Yuncheng Wu, Shaofeng Cai, Xiaokui Xiao +2
Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other. This paper studies…
HelPal: A Search System for Mobile Crowd Service
Yao Wu, Tianzhen Wu, Ziyi Xiong +4
Proliferation of ubiquitous mobile devices makes location based services prevalent. Mobile users are able to volunteer as providers of specific services and in the meanwhile to sea…