v1v2 (latest)

PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage

IEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2021

10 August 2021

ArXiv (abs)PDF HTML Github (10★)

Papers citing "PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage"

23 / 23 papers shown

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training

350

28 Nov 2025

SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition

244

01 Oct 2025

Evaluating Selective Encryption Against Gradient Inversion Attacks

135

06 Aug 2025

DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems

209

02 Jun 2025

Empirical Calibration and Metric Differential Privacy in Language Models

306

18 Mar 2025

FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses

427

05 Nov 2024

Gradients Stand-in for Defending Deep Leakage in Federated Learning

250

11 Oct 2024

Analyzing Inference Privacy Risks Through Gradients in Machine LearningConference on Computer and Communications Security (CCS), 2024

Bradley Malin

Ye Wang

FedML

381

29 Aug 2024

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks

Sayedeh Leila Noorbakhsh

336

04 Mar 2024

Toward the Tradeoffs between Privacy, Fairness and Utility in Federated LearningInternational Symposium on Emerging Information Security and Applications (EISA), 2023

Gaolei Li

197

30 Nov 2023

A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective

312

27 Nov 2023

Understanding Deep Gradient Leakage via Inversion Influence FunctionsNeural Information Processing Systems (NeurIPS), 2023

468

22 Sep 2023

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks

408

08 Sep 2023

Privacy and Fairness in Federated Learning: on the Perspective of Trade-offACM Computing Surveys (ACM Comput. Surv.), 2023

Philip S. Yu

345

25 Jun 2023

Gradient Leakage Defense with Key-Lock Module for Federated Learning

527

06 May 2023

Directional Privacy for Deep Learning

Pedro Faustini

Natasha Fernandes

Shakila Mahjabin Tonni

Annabelle McIver

Mark Dras

366

09 Nov 2022

A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning

249

08 Sep 2022

Dropout is NOT All You Need to Prevent Gradient LeakageAAAI Conference on Artificial Intelligence (AAAI), 2022

324

12 Aug 2022

Data Leakage in Federated Averaging

Martin Vechev

391

24 Jun 2022

Gradient Obfuscation Gives a False Sense of Security in Federated LearningUSENIX Security Symposium (USENIX Security), 2022

Chau-Wai Wong

294

08 Jun 2022

LAMP: Extracting Text from Gradients with Language Model PriorsNeural Information Processing Systems (NeurIPS), 2022

Mislav Balunović

Dimitar I. Dimitrov

Nikola Jovanović

Martin Vechev

409

17 Feb 2022

Bayesian Framework for Gradient Leakage

Martin Vechev

275

08 Nov 2021

Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated LearningACM Transactions on Knowledge Discovery from Data (TKDD), 2020

Xinjian Luo

Xiangqi Zhu

FedML

819

27 Apr 2020