Image de couverture de livre

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Schuchardt, Jan, Kalinin, Nikita
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
par: Schuchardt, Jan, et autres
Publié: (2024)

Amplified Patch-Level Differential Privacy for Free via Random Cropping
par: Durmaz, Kaan, et autres
Publié: (2026)

Banded Square Root Matrix Factorization for Differentially Private Model Training
par: Kalinin, Nikita P., et autres
Publié: (2024)

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
par: Saxena, Aman, et autres
Publié: (2026)

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
par: Schuchardt, Jan, et autres
Publié: (2025)

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
par: Schuchardt, Jan, et autres
Publié: (2023)

Privacy Amplification for Matrix Mechanisms
par: Choquette-Choo, Christopher A., et autres
Publié: (2023)

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
par: Kalinin, Nikita P., et autres
Publié: (2025)

Normalized Square Root: Sharper Matrix Factorization Bounds for Differentially Private Continual Counting
par: Henzinger, Monika, et autres
Publié: (2025)

Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
par: Lebeda, Christian Janos, et autres
Publié: (2024)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
par: Kalinin, Nikita P., et autres
Publié: (2024)

Auditing Privacy in Multi-Tenant RAG under Account Collusion
par: Burnat, Florian A. D.
Publié: (2026)

Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
par: Damie, Marc, et autres
Publié: (2025)

Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy
par: Hidano, Seira, et autres
Publié: (2022)

Privacy for Free in the Overparameterized Regime
par: Bombari, Simone, et autres
Publié: (2024)

The Sample Complexity of Membership Inference and Privacy Auditing
par: Haghifam, Mahdi, et autres
Publié: (2025)

Personalized Privacy Amplification via Importance Sampling
par: Fay, Dominik, et autres
Publié: (2023)

On the Privacy of Selection Mechanisms with Gaussian Noise
par: Lebensold, Jonathan, et autres
Publié: (2024)

Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication
par: Ma, Xirong
Publié: (2023)

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
par: Dong, Andy, et autres
Publié: (2025)

Purifying Approximate Differential Privacy with Randomized Post-processing
par: Lin, Yingyu, et autres
Publié: (2025)

Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration
par: Pierquin, Clément, et autres
Publié: (2023)

FRIDA: Free-Rider Detection using Privacy Attacks
par: Recasens, Pol G., et autres
Publié: (2024)

Differential Privacy in Kernelized Contextual Bandits via Random Projections
par: Pavlovic, Nikola, et autres
Publié: (2025)

Optimal Fairness under Local Differential Privacy
par: Ghoukasian, Hrad, et autres
Publié: (2025)

Optimality of Matrix Mechanism on $\ell_p^p$-metric
par: Liu, Jingcheng, et autres
Publié: (2024)

Privacy Amplification for the Gaussian Mechanism via Bounded Support
par: Hu, Shengyuan, et autres
Publié: (2024)

Auditing Privacy Mechanisms via Label Inference Attacks
par: Busa-Fekete, Róbert István, et autres
Publié: (2024)

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy
par: You, Zhichao, et autres
Publié: (2025)

Deep Learning under Fractional-Order Differential Privacy
par: Partohaghighi, Mohammad, et autres
Publié: (2026)

On the Alignment of Group Fairness with Attribute Privacy
par: Aalmoes, Jan, et autres
Publié: (2022)

On the Statistical Complexity of Estimation and Testing under Privacy Constraints
par: Lalanne, Clément, et autres
Publié: (2022)

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
par: Chen, Wei-Ning, et autres
Publié: (2024)

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
par: Pal, Arka, et autres
Publié: (2026)

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
par: Wu, Haoqi, et autres
Publié: (2025)

Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy
par: Xu, Jiahao, et autres
Publié: (2025)

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
par: Greenewald, Kristjan, et autres
Publié: (2024)

Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods
par: Pollock, Joseph, et autres
Publié: (2024)

P3LS: Partial Least Squares under Privacy Preservation
par: Duy, Du Nguyen, et autres
Publié: (2024)

On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
par: Wang, Zijian, et autres
Publié: (2025)