Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?
Authors: Hao Du, Shang Liu, Yang Cao | Published: 2025-04-28 | Updated: 2025-05-01
メンバーシップ開示リスク
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
Authors: Ken Ziyu Liu, Christopher A. Choquette-Choo, Matthew Jagielski, Peter Kairouz, Sanmi Koyejo, Percy Liang, Nicolas Papernot | Published: 2025-03-21 | Updated: 2025-03-25
Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
Authors: Xiaoyu Wu, Yifei Pang, Terrance Liu, Steven Wu | Published: 2025-03-15
Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation method
Authors: Rémy Chapelle, Bruno Falissard | Published: 2023-10-10
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage
Authors: Catherine Huang, Chelse Swoopes, Christina Xiao, Jiaqi Ma, Himabindu Lakkaraju | Published: 2023-08-08
On the Discredibility of Membership Inference Attacks
Authors: Shahbaz Rezaei, Xin Liu | Published: 2022-12-06 | Updated: 2023-04-28
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
Authors: Lucas Lange, Maja Schneider, Peter Christen, Erhard Rahm | Published: 2022-11-21 | Updated: 2023-04-26
Provable Membership Inference Privacy
Authors: Zachary Izzo, Jinsung Yoon, Sercan O. Arik, James Zou | Published: 2022-11-12
Amplifying Membership Exposure via Data Poisoning
Authors: Yufei Chen, Chao Shen, Yun Shen, Cong Wang, Yang Zhang | Published: 2022-11-01
On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models
Authors: Mauro Conti, Jiaxin Li, Stjepan Picek | Published: 2022-10-28