Image de couverture de livre

PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Qin, Stout, Nicholas, Mohammady, Meisam, Wang, Han, Samreen, Ayesha, Quinn, Christopher J, Yan, Yan, Kundu, Ashish, Hong, Yuan
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
par: Mohammady, Meisam, et autres
Publié: (2026)

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
par: Feng, Shuya, et autres
Publié: (2024)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
par: Yang, Qin, et autres
Publié: (2024)

DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming
par: Feng, Shuya, et autres
Publié: (2023)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
par: Zhang, Xinwei, et autres
Publié: (2024)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
par: Lowy, Andrew, et autres
Publié: (2021)

Advances in Differential Privacy and Differentially Private Machine Learning
par: Das, Saswat, et autres
Publié: (2024)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
par: Zhang, Xinwei, et autres
Publié: (2024)

Advancing Honeywords for Real-World Authentication Security
par: Das, Sudiksha, et autres
Publié: (2025)

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
par: Liang, Hao, et autres
Publié: (2025)

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
par: Lowy, Andrew, et autres
Publié: (2021)

Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems
par: Nissim, Kobbi, et autres
Publié: (2025)

Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter
par: Lowy, Andrew, et autres
Publié: (2022)

Differentially Private Next-Token Prediction of Large Language Models
par: Flemings, James, et autres
Publié: (2024)

Optimal Differentially Private Model Training with Public Data
par: Lowy, Andrew, et autres
Publié: (2023)

Towards Strong Certified Defense with Universal Asymmetric Randomization
par: Hong, Hanbin, et autres
Publié: (2025)

Private Linear Regression with Differential Privacy and PAC Privacy
par: Yang, Hillary, et autres
Publié: (2024)

PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
par: Kundu, Ripan Kumar, et autres
Publié: (2025)

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

Enhancing Accuracy-Privacy Trade-off in Differentially Private Split Learning
par: Pham, Ngoc Duy, et autres
Publié: (2023)

The Quantum-Cryptographic Co-evolution
par: Kundu, Ashish, et autres
Publié: (2026)

Adaptively Private Next-Token Prediction of Large Language Models
par: Flemings, James, et autres
Publié: (2024)

Interpreting Differential Privacy in Terms of Disclosure Risk
par: Kazan, Zeki, et autres
Publié: (2025)

Bipartite Randomized Response Mechanism for Local Differential Privacy
par: Zhang, Shun, et autres
Publié: (2025)

Differentially Private Random Feature Model
par: Liao, Chunyang, et autres
Publié: (2024)

Computationally Differentially Private Inner Product Protocols Imply Oblivious Transfer
par: Haitner, Iftach, et autres
Publié: (2025)

A Decade of Metric Differential Privacy: Advancements and Applications
par: Xie, Xinpeng, et autres
Publié: (2025)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
par: Yu, Da, et autres
Publié: (2022)

Differentially Private Decentralized Learning with Random Walks
par: Cyffers, Edwige, et autres
Publié: (2024)

DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
par: Liu, Yixuan, et autres
Publié: (2024)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
par: Sha, Haichao, et autres
Publié: (2023)

An $\tilde{O}$ptimal Differentially Private Learner for Concept Classes with VC Dimension 1
par: Yan, Chao
Publié: (2025)

On Improving the Composition Privacy Loss in Differential Privacy for Fixed Estimation Error
par: Rameshwar, V. Arvind, et autres
Publié: (2024)

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
par: Zhu, Sichen, et autres
Publié: (2025)

Tight Differential Privacy Guarantees for the Shuffle Model with $k$-Randomized Response
par: Biswas, Sayan, et autres
Publié: (2022)

Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy
par: Ryu, Sehyun, et autres
Publié: (2024)

Dobrushin Coefficients of Private Mechanisms Beyond Local Differential Privacy
par: Grosse, Leonhard, et autres
Publié: (2026)

Protecting Private Code in IDE Autocomplete using Differential Privacy
par: Grigorenko, Evgeny, et autres
Publié: (2026)

Differentially Private Relational Learning with Entity-level Privacy Guarantees
par: Huang, Yinan, et autres
Publié: (2025)

Calibrating Practical Privacy Risks for Differentially Private Machine Learning
par: Gu, Yuechun, et autres
Publié: (2024)