6 papers · 1 filter
QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery
Yufan Zhu, Yangfan Jiang, Yang Fei +3
Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call such a jointly revealing set…
Distributed and Private Textual Data Synthesis from Embeddings
Ergute Bao, Hongyan Chang, Ali Shahin Shamsabadi +2
We revisit differentially private (DP) text synthesis in the realistic setting of distributed users, where privacy concerns preclude a trusted curator with access to raw user texts…
Private Direct Preference Optimization for LLM Alignment
Yangfan Jiang, Fei Wei, Ergute Bao +3
Direct preference optimization (DPO) is now a standard method for aligning large language models (LLMs) using human preference data. Each DPO example contains a prompt and a pair o…
Benchmarking Text-to-SQL under Role-Based Access Control
Yang Fei, Yangfan Jiang, Yin Yang +1
Given a database S and a natural language question Q, text-to-SQL systems aim to generate an SQL query that correctly answers Q when executed against S. Currently, popular text-to-…
Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks
Rishav Chourasia, Ergute Bao, Uzair Javaid +1
Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy (DP). Apple's DifferentialPrivacy framework is deploy…
Accurate Table Question Answering with Accessible LLMs
Yangfan Jiang, Fei Wei, Ergute Bao +4
Given a table T in a database and a question Q in natural language, the table question answering (TQA) task aims to return an accurate answer to Q based on the content of T. Recent…