paper-with-me

홈 › Papers

VaultGemma: A Differentially Private Gemma Model

2025-10-15 · Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan Zhang, Badih Ghazi, Borja De Balle Pigem, Prem Eruvbetine, Tris Warkentin, Armand Joulin, Ravi Kumar arxiv

We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemma 2 series, VaultGemma 1B represents a significant step forward in privacy-preserving large language models. We openly release this model to the community

📄 PDF Abstract BibTeX arXiv:2510.15001

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling

2026-03-23 · Young Hyun Cho, Will Wei Sun arxiv

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differential…

Reinforcement Learning

Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs

2025-01-31 · James Flemings, Haosheng Gan, Hongyi Li, Meisam Razaviyayn 외

In-context learning (ICL) has shown promising improvement in downstream task adaptation of LLMs by augmenting prompts with relevant input-output examples (demonstrations). However, the ICL demonstrations can contain priv…

Few-Shot LearningIn-Context Learning

Reconstruction of Differentially Private Text Sanitization via Large Language Models

2024-10-16 · Shuchao Pang, Zhigang Lu, Haichen Wang, Peng Fu 외

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct…

Differentially Private Algorithms for Empirical Machine Learning

2014-11-20 · Ben Stoddard, Yan Chen, Ashwin Machanavajjhala

An important use of private data is to build machine learning classifiers. While there is a burgeoning literature on differentially private classification algorithms, we find that they are not practical in real applicati…

BIG-bench Machine LearningGeneral Classification

Adaptive Differentially Private Empirical Risk Minimization

2021-10-14 · Xiaoxia Wu, Lingxiao Wang, Irina Cristali, Quanquan Gu 외

We propose an adaptive (stochastic) gradient perturbation method for differentially private empirical risk minimization. At each iteration, the random noise added to the gradient is optimally adapted to the stepsize; we …