Buchumschlag

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Feng, Shuya, Mohammady, Meisam, Hong, Hanbin, Yan, Shenao, Kundu, Ashish, Wang, Binghui, Hong, Yuan
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming
von: Feng, Shuya, et al.
Veröffentlicht: (2023)

Towards Strong Certified Defense with Universal Asymmetric Randomization
von: Hong, Hanbin, et al.
Veröffentlicht: (2025)

PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
von: Yang, Qin, et al.
Veröffentlicht: (2025)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
von: Yang, Qin, et al.
Veröffentlicht: (2024)

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
von: Naderloui, Nima, et al.
Veröffentlicht: (2025)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
von: Noorbakhsh, Sayedeh Leila, et al.
Veröffentlicht: (2024)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
von: Hong, Hanbin, et al.
Veröffentlicht: (2023)

Learning Robust and Privacy-Preserving Representations via Information Theory
von: Zhang, Binghui, et al.
Veröffentlicht: (2024)

Convergent Differential Privacy Analysis for General Federated Learning
von: Sun, Yan, et al.
Veröffentlicht: (2024)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
von: Zhang, Xinwei, et al.
Veröffentlicht: (2024)

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
von: Mohammady, Meisam, et al.
Veröffentlicht: (2026)

SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models
von: Hong, Hanbin, et al.
Veröffentlicht: (2025)

Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
von: Bao, Ergute, et al.
Veröffentlicht: (2022)

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
von: Zhang, Xinyu, et al.
Veröffentlicht: (2023)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
von: Wang, Zifan, et al.
Veröffentlicht: (2024)

Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
von: Liang, Hao, et al.
Veröffentlicht: (2025)

Backdoor Attacks on Discrete Graph Diffusion Models
von: Wang, Jiawen, et al.
Veröffentlicht: (2025)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
von: Lowy, Andrew, et al.
Veröffentlicht: (2021)

Federated Transfer Learning with Differential Privacy
von: Li, Mengchu, et al.
Veröffentlicht: (2024)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
von: Zhang, Xinwei, et al.
Veröffentlicht: (2024)

Efficient Federated Unlearning with Adaptive Differential Privacy Preservation
von: Jiang, Yu, et al.
Veröffentlicht: (2024)

Differentially Private Federated Learning: A Systematic Review
von: Fu, Jie, et al.
Veröffentlicht: (2024)

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy
von: You, Zhichao, et al.
Veröffentlicht: (2025)

Towards Explainable Federated Learning: Understanding the Impact of Differential Privacy
von: Oliveira, Júlio, et al.
Veröffentlicht: (2026)

Complex-valued Federated Learning with Differential Privacy and MRI Applications
von: Riess, Anneliese, et al.
Veröffentlicht: (2021)

A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
von: Li, Xiang, et al.
Veröffentlicht: (2025)

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
von: Wu, Haoqi, et al.
Veröffentlicht: (2025)

A Learning-Based Attack Framework to Break SOTA Poisoning Defenses in Federated Learning
von: Yang, Yuxin, et al.
Veröffentlicht: (2024)

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
von: Lowy, Andrew, et al.
Veröffentlicht: (2021)

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
von: Yan, Shenao, et al.
Veröffentlicht: (2024)

On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
von: Wang, Zijian, et al.
Veröffentlicht: (2025)

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
von: Nie, Chenfei, et al.
Veröffentlicht: (2024)

DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secure Aggregation
von: Wei, Wenjing, et al.
Veröffentlicht: (2026)

Federated Learning in Genetics: Extended Analysis of Accuracy, Performance and Privacy Trade-offs
von: Hannemann, Anika, et al.
Veröffentlicht: (2024)

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
von: Jin, Richeng, et al.
Veröffentlicht: (2023)

Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations
von: Hong, Sanghyun, et al.
Veröffentlicht: (2025)

ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
von: Kato, Fumiyuki, et al.
Veröffentlicht: (2023)

Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates
von: Wang, Chuanyin, et al.
Veröffentlicht: (2025)