138 citations · 201 across the 13 of their papers we have counts for
14 papers
Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
Terrance Liu, Matteo Boglioni, Yiwei Fu +3
Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many traini…
Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
Xiaoyu Wu, Yifei Pang, Terrance Liu +1
Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privac…
Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies
Terrance Liu, Shuyi Wang, Daniel Preotiuc-Pietro +2
While large language models (LLMs) achieve strong performance on text-to-SQL parsing, they sometimes exhibit unexpected failures in which they are confidently incorrect. Building t…
Generate-then-Verify: Reconstructing Data from Limited Published Statistics
Terrance Liu, Eileen Xiao, Adam Smith +2
We study the problem of reconstructing tabular data from aggregate statistics, in which the attacker aims to identify interesting claims about the sensitive data that can be verifi…
Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
Xiaoyu Wu, Yifei Pang, Terrance Liu +1
Tabular data synthesis using diffusion models has gained significant attention for its potential to balance data utility and privacy. However, existing privacy evaluations often re…
Multi-group Uncertainty Quantification for Long-form Text Generation
Terrance Liu, Zhiwei Steven Wu
While past works have shown how uncertainty quantification can be applied to large language model (LLM) outputs, the question of whether resulting uncertainty guarantees still hold…
Generating Private Synthetic Data with Genetic Algorithms
Terrance Liu, Jingwu Tang, Giuseppe Vietri +1
We study the problem of efficiently generating differentially private synthetic data that approximate the statistical properties of an underlying sensitive dataset. In recent years…
Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
Travis Dick, Cynthia Dwork, Michael Kearns +4
A reconstruction attack on a private dataset takes as input some publicly accessible information about the dataset and produces a list of candidate elements of . We introduc…
Private Synthetic Data with Hierarchical Structure
Terrance Liu, Zhiwei Steven Wu
We study the problem of differentially private synthetic data generation for hierarchical datasets in which individual data points are grouped together (e.g., people within househo…
Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data
Paul Pu Liang, Terrance Liu, Anna Cai +7
Mental health conditions remain underdiagnosed even in countries with common access to advanced medical care. The ability to accurately and efficiently predict mood from easily col…
Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods
Terrance Liu, Giuseppe Vietri, Zhiwei Steven Wu
We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that appro…
Leveraging Public Data for Practical Private Query Release
Terrance Liu, Giuseppe Vietri, Thomas Steinke +2
In many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained u…
Multimodal Privacy-preserving Mood Prediction from Mobile Data: A Preliminary Study
Terrance Liu, Paul Pu Liang, Michal Muszynski +5
Mental health conditions remain under-diagnosed even in countries with common access to advanced medical care. The ability to accurately and efficiently predict mood from easily co…
Think Locally, Act Globally: Federated Learning with Local and Global Representations
Paul Pu Liang, Terrance Liu, Liu Ziyin +5
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating…