Image de couverture de livre

VaultGemma: A Differentially Private Gemma Model

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sinha, Amer, Mesnard, Thomas, McKenna, Ryan, Liu, Daogao, Choquette-Choo, Christopher A., Huang, Yangsibo, Yu, Da, Kaissis, George, Charles, Zachary, Liu, Ruibo, Chua, Lynn, Kamath, Pritish, Manurangsi, Pasin, He, Steve, Zhang, Chiyuan, Ghazi, Badih, Pigem, Borja De Balle, Eruvbetine, Prem, Warkentin, Tris, Joulin, Armand, Kumar, Ravi
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
par: Chua, Lynn, et autres
Publié: (2024)

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
par: Huang, Yangsibo, et autres
Publié: (2024)

Scalable DP-SGD: Shuffling vs. Poisson Subsampling
par: Chua, Lynn, et autres
Publié: (2024)

How Private are DP-SGD Implementations?
par: Chua, Lynn, et autres
Publié: (2024)

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
par: Chua, Lynn, et autres
Publié: (2024)

Private Hyperparameter Tuning with Ex-Post Guarantee
par: Ghazi, Badih, et autres
Publié: (2025)

On Convex Optimization with Semi-Sensitive Features
par: Ghazi, Badih, et autres
Publié: (2024)

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization
par: Ghazi, Badih, et autres
Publié: (2024)

Denoising the US Census: Succinct Block Hierarchical Regression
par: Ghazi, Badih, et autres
Publié: (2026)

Differentially Private Optimization with Sparse Gradients
par: Ghazi, Badih, et autres
Publié: (2024)

On Computing Pairwise Statistics with Local Differential Privacy
par: Ghazi, Badih, et autres
Publié: (2024)

Linear-Time User-Level DP-SCO via Robust Statistics
par: Ghazi, Badih, et autres
Publié: (2025)

Scaling Embedding Layers in Language Models
par: Yu, Da, et autres
Publié: (2025)

Balls-and-Bins Sampling for DP-SGD
par: Chua, Lynn, et autres
Publié: (2024)

Computational Hardness of Private Coreset
par: Ghazi, Badih, et autres
Publié: (2026)

Urania: Differentially Private Insights into AI Use
par: Liu, Daogao, et autres
Publié: (2025)

Scaling Laws for Differentially Private Language Models
par: McKenna, Ryan, et autres
Publié: (2025)

PREM: Privately Answering Statistical Queries with Relative Error
par: Ghazi, Badih, et autres
Publié: (2025)

When Majority Fails: Tight Bounds for Correlation Distillation Conjectures
par: Kamath, Pritish, et autres
Publié: (2026)

Convex Optimization with Local Label Differential Privacy: Tight Bounds in All Privacy Regimes
par: Chua, Lynn, et autres
Publié: (2026)

CodeGemma: Open Code Models Based on Gemma
par: CodeGemma Team, et autres
Publié: (2024)

How Unique is Whose Web Browser? The role of demographics in browser fingerprinting among US users
par: Berke, Alex, et autres
Publié: (2024)

T5Gemma 2: Seeing, Reading, and Understanding Longer
par: Zhang, Biao, et autres
Publié: (2025)

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features
par: Chua, Lynn, et autres
Publié: (2024)

Differential Privacy on Trust Graphs
par: Ghazi, Badih, et autres
Publié: (2024)

Quantifying Cross-Modality Memorization in Vision-Language Models
par: Wen, Yuxin, et autres
Publié: (2025)

MedGemma Technical Report
par: Sellergren, Andrew, et autres
Publié: (2025)

Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation
par: Zhang, Biao, et autres
Publié: (2025)

On the Differential Privacy and Interactivity of Privacy Sandbox Reports
par: Ghazi, Badih, et autres
Publié: (2024)

Gemma 3 Technical Report
par: Gemma Team, et autres
Publié: (2025)

EmbeddingGemma: Powerful and Lightweight Text Representations
par: Vera, Henrique Schechter, et autres
Publié: (2025)

ShieldGemma: Generative AI Content Moderation Based on Gemma
par: Zeng, Wenjun, et autres
Publié: (2024)

MedGemma 1.5 Technical Report
par: Sellergren, Andrew, et autres
Publié: (2026)

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
par: Botev, Aleksandar, et autres
Publié: (2024)

Gemma: Open Models Based on Gemini Research and Technology
par: Gemma Team, et autres
Publié: (2024)

Improved Approximation Algorithm for Maximum Balanced Biclique
par: Manurangsi, Pasin
Publié: (2026)

Improved Lower Bound for Differentially Private Facility Location
par: Manurangsi, Pasin
Publié: (2024)

On Expansion of Random Regular Graphs: Improved Lower Bounds for Small Even Degrees
par: Manurangsi, Pasin
Publié: (2026)

Improved FPT Approximation Scheme and Approximate Kernel for Biclique-Free Max k-Weight SAT: Greedy Strikes Back
par: Manurangsi, Pasin
Publié: (2024)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
par: Lieberum, Tom, et autres
Publié: (2024)