73 citations · 157 across the 15 of their papers we have counts for
9 papers · 1 filter
On the Cause of Unfairness: A Training Sample Perspective
Yuanshun Yao, Yang Liu
Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unf…
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes
Zhaowei Zhu, Yuanshun Yao, Jiankai Sun +2
Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry…
DPAUC: Differentially Private AUC Computation in Federated Learning
Jiankai Sun, Xin Yang, Yuanshun Yao +3
Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on…
Differentially Private AUC Computation in Vertical Federated Learning
Jiankai Sun, Xin Yang, Yuanshun Yao +3
Federated learning has gained great attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple parties. As a sub-category, vertical federa…
Differentially Private Label Protection in Split Learning
Xin Yang, Jiankai Sun, Yuanshun Yao +2
Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attribute…
Label Leakage and Protection from Forward Embedding in Vertical Federated Learning
Jiankai Sun, Xin Yang, Yuanshun Yao +1
Vertical federated learning (vFL) has gained much attention and been deployed to solve machine learning problems with data privacy concerns in recent years. However, some recent wo…
Defending against Reconstruction Attack in Vertical Federated Learning
Jiankai Sun, Yuanshun Yao, Weihao Gao +2
Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared…
Vertical Federated Learning without Revealing Intersection Membership
Jiankai Sun, Xin Yang, Yuanshun Yao +4
Vertical Federated Learning (vFL) allows multiple parties that own different attributes (e.g. features and labels) of the same data entity (e.g. a person) to jointly train a model.…
Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks
Yuanshun Yao, Huiying Li, Haitao Zheng +1
Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific…