6 papers
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…
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…
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…
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…