Mind the Privacy Unit! User-Level Differential Privacy for Language
Model Fine-Tuning

v1v2v3 (latest)

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

20 June 2024

Yangsibo Huang

Pasin Manurangsi

ArXiv (abs)PDF HTML

Papers citing "Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning"

13 / 13 papers shown

Title
Auditable Early Stopping for Agentic Routing: Ledger-Verified Run-Wise Certificates under Local DP Shivam Akhauri 148 0 0 09 Sep 2025
Black-Box Privacy Attacks on Shared Representations in Multitask Learning John Abascal Nicolás Berrios Alina Oprea Jonathan R. Ullman Adam D. Smith Matthew Jagielski MLAU 196 0 0 19 Jun 2025
Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Arun Ganesh Brendan McMahan Milad Nasr Thomas Steinke Abhradeep Thakurta 157 1 0 30 May 2025
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data Tong Chen Faeze Brahman Hamish Ivison Niloofar Mireshghallah Weijia Shi Pang Wei Koh Luke Zettlemoyer Hannaneh Hajishirzi 244 3 0 20 Apr 2025
Empirical Privacy Variance Yuzheng Hu Fan Wu Ruicheng Xian Yuhang Liu Lydia Zakynthinou Pritish Kamath Chiyuan Zhang David A. Forsyth 403 1 0 16 Mar 2025
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational AgentsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Ivoline Ngong Swanand Kadhe Hao Wang K. Murugesan Justin D. Weisz Amit Dhurandhar Karthikeyan N. Ramamurthy 219 12 0 22 Feb 2025
Towards User-level Private Reinforcement Learning with Human Feedback Jing Zhang Mingxi Lei Meng Ding Mengdi Li Zihang Xiang Difei Xu Jinhui Xu Di Wang 211 5 0 22 Feb 2025
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models Olivia Ma Jonathan Passerat-Palmbach Dmitrii Usynin 318 2 0 24 Nov 2024
Evaluating Differentially Private Synthetic Data Generation in High-Stakes DomainsConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 Krithika Ramesh Nupoor Gandhi Pulkit Madaan Lisa Bauer Charith Peris Anjalie Field SyDa 154 10 0 10 Oct 2024
A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs H. B. McMahan Zheng Xu Yanxiang Zhang FedML 356 9 0 16 Aug 2024
Fine-Tuning Large Language Models with User-Level Differential Privacy Zachary Charles Arun Ganesh Ryan McKenna H. B. McMahan Nicole Mitchell Krishna Pillutla Keith Rush 229 33 0 10 Jul 2024
User Inference Attacks on Large Language Models Nikhil Kandpal Krishna Pillutla Alina Oprea Peter Kairouz Christopher A. Choquette-Choo Zheng Xu SILM AAML 309 31 0 13 Oct 2023
Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model ServicesIEEE Transactions on Audio, Speech, and Language Processing (IEEE TASLP), 2023 Yansong Li Zhixing Tan Paula Branco Yang Liu SILM VLM 395 78 0 10 May 2023