73 citations · 157 across the 15 of their papers we have counts for
16 papers
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Yang Liu, Yuanshun Yao, Jean-Francois Ton +6
Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real…
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…
Label Inference Attack against Split Learning under Regression Setting
Shangyu Xie, Xin Yang, Yuanshun Yao +3
As a crucial building block in vertical Federated Learning (vFL), Split Learning (SL) has demonstrated its practice in the two-party model training collaboration, where one party h…
Learning to Counterfactually Explain Recommendations
Yuanshun Yao, Chong Wang, Hang Li
Recommender system practitioners are facing increasing pressure to explain recommendations. We explore how to explain recommendations using counterfactual logic, i.e. "Had you not…
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 Multi-Party Data Release for Linear Regression
Ruihan Wu, Xin Yang, Yuanshun Yao +4
Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focu…
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…
Counterfactually Evaluating Explanations in Recommender Systems
Yuanshun Yao, Chong Wang, Hang Li
Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a si…
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.…
Backdoor Attacks Against Deep Learning Systems in the Physical World
Emily Wenger, Josephine Passananti, Arjun Bhagoji +3
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existin…
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…
Automated Crowdturfing Attacks and Defenses in Online Review Systems
Yuanshun Yao, Bimal Viswanath, Jenna Cryan +2
Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers. In this paper,…