Recover User’s Private Training Image Data by Gradient in Federated Learning

Recover User’s Private Training Image Data by Gradient in Federated Learning

Exchanging gradient is a widely used method in modern multinode machine learning system (e.g., distributed training, Federated Learning). Gradients and weights of model has been presumed to be safe to delivery. However, some studies have shown that gradient inversion technique can reconstruct the in...

Full description

Bibliographic Details
Main Authors:	Haimei Gong, Liangjun Jiang, Xiaoyang Liu, Yuanqi Wang, Lei Wang, Ke Zhang
Format:	Article
Language:	English
Published:	MDPI AG 2022-09-01
Series:	Sensors
Subjects:	security and privacy Federated Learning data reconstruction attack gradient leakage attacks
Online Access:	https://www.mdpi.com/1424-8220/22/19/7157

Similar Items

Evaluating the Impact of Mobility on Differentially Private Federated Learning
by: Eun-ji Kim, et al.
Published: (2024-06-01)

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data
by: Joceline Ziegler, et al.
Published: (2022-07-01)

MPHM: Model poisoning attacks on federal learning using historical information momentum
by: Shi Lei, et al.
Published: (2023-01-01)

A Critical Evaluation of Privacy and Security Threats in Federated Learning
by: Muhammad Asad, et al.
Published: (2020-12-01)

Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives
by: Pengrui Liu, et al.
Published: (2022-02-01)

Survey on model inversion attack and defense in federated learning
by: Dong WANG, et al.
Published: (2023-11-01)

Survey on model inversion attack and defense in federated learning
by: Dong WANG, et al.
Published: (2023-11-01)

Survey on vertical federated learning: algorithm, privacy and security
by: Jinyin CHEN, et al.
Published: (2023-04-01)

Survey on vertical federated learning: algorithm, privacy and security
by: Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG
Published: (2023-04-01)

HAFedL: A Hessian-Aware Adaptive Privacy Preserving Horizontal Federated Learning Scheme for IoT Applications
by: Sumitra, et al.
Published: (2024-01-01)

FL-AGN: A Privacy-Enhanced Federated Learning Method Based on Adaptive Gaussian Noise for Resisting Gradient Inference Attacks
by: Zhifu Huang, et al.
Published: (2024-01-01)

Blockchain-Based Swarm Learning for the Mitigation of Gradient Leakage in Federated Learning
by: Hussain Ahmad Madni, et al.
Published: (2023-01-01)

Federated Learning Based Privacy Ensured Sensor Communication in IoT Networks: A Taxonomy, Threats and Attacks
by: Sheikh Imroza Manzoor, et al.
Published: (2023-01-01)

Secure federated learning scheme based on adaptive Byzantine defense
by: ZHOU Yousheng, et al.
Published: (2024-08-01)

Secure federated learning scheme based on adaptive Byzantine defense
by: ZHOU Yousheng, et al.
Published: (2024-08-01)

Differential Private Federated Learning in Geographically Distributed Public Administration Processes
by: Mirwais Ahmadzai, et al.
Published: (2024-06-01)

Privacy-Preserving Image Template Sharing Using Contrastive Learning
by: Shideh Rezaeifar, et al.
Published: (2022-05-01)

Membership inference attack and defense method in federated learning based on GAN
by: Jiale ZHANG, et al.
Published: (2023-05-01)

Membership inference attack and defense method in federated learning based on GAN
by: Jiale ZHANG, et al.
Published: (2023-05-01)

Dynamic Asynchronous Anti Poisoning Federated Deep Learning with Blockchain-Based Reputation-Aware Solutions
by: Zunming Chen, et al.
Published: (2022-01-01)

Threats and defenses of federated learning: a survey
by: Jianhan WU, et al.
Published: (2022-09-01)

Research advances on privacy protection of federated learning
by: Jianzong WANG, et al.
Published: (2021-05-01)

Adversarial attacks on videos based on the conjugate gradient method
by: Yang DAI, et al.
Published: (2024-09-01)

A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
by: Habib Ullah Manzoor, et al.
Published: (2024-10-01)

Privacy-enhanced federated learning scheme based on generative adversarial networks
by: Feng YU, et al.
Published: (2023-06-01)

Privacy-enhanced federated learning scheme based on generative adversarial networks
by: Feng YU, Qingxin LIN, Hui LIN, Xiaoding WANG
Published: (2023-06-01)

On Vehicular Data Aggregation in Federated Learning
by: Levente Alekszejenkó, et al.
Published: (2024-07-01)

Comparative Analysis of Membership Inference Attacks in Federated and Centralized Learning
by: Ali Abbasi Tadi, et al.
Published: (2023-11-01)

MS-FL: A Federated Learning Framework Based on Multiple Security Strategies
by: Wenshao Yang, et al.
Published: (2024-01-01)

Iterative and mixed-spaces image gradient inversion attack in federated learning
by: Linwei Fang, et al.
Published: (2024-04-01)

Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
by: Gergely D. Nemeth, et al.
Published: (2025-01-01)

DAGUARD: distributed backdoor attack defense scheme under federated learning
by: Shengxing YU, et al.
Published: (2023-05-01)

DAGUARD: distributed backdoor attack defense scheme under federated learning
by: Shengxing YU, et al.
Published: (2023-05-01)

Reconstruction Attacks on Aggressive Relaxations of Differential Privacy
by: Prottay Protivash, et al.
Published: (2024-08-01)

Untargeted Poisoning Attack Detection in Federated Learning via Behavior AttestationAl
by: Ranwa Al Mallah, et al.
Published: (2023-01-01)

Gradient purification federated adaptive learning algorithm for Byzantine attack resistance
by: YANG Hui, et al.
Published: (2024-10-01)

Edge computing privacy protection method based on blockchain and federated learning
by: Chen FANG, et al.
Published: (2021-11-01)

Edge computing privacy protection method based on blockchain and federated learning
by: Chen FANG, et al.
Published: (2021-11-01)

Balancing Privacy and Performance: A Differential Privacy Approach in Federated Learning
by: Huda Kadhim Tayyeh, et al.
Published: (2024-10-01)

VAEFL: Integrating variational autoencoders for privacy preservation and performance retention in federated learning
by: Li Zhixin, et al.
Published: (2024-01-01)