Decentralized Federated Learning: A Defense Against Gradient Inversion Attack

Guang-xi, LU; Xiong, Zuobin; Li, Ruinian; Li, Wei

doi:10.1007/978-3-031-27041-3_4

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a decentralized federated learning system, participants communicate with each other without the coordination of an aggregation server. Lu et al [68] proposed a decentralized federated learning (DFL) method to defend against gradient reversal attacks, and demonstrated its security capabilities in a depth gradient leakage (DLG) environment, as shown in Figure 9. Li et al [69] performs a cluster analysis on model parameters to distinguish good and bad models, and then detect potential malicious participants.…”

Section: Build a Trusted Federated Learning Systemmentioning

confidence: 99%

Challenges and Countermeasures of Federated Learning Data Poisoning Attack Situation Prediction

Wu,

Jin,

2024

Mathematics

View full text Add to dashboard Cite

Federated learning is a distributed learning method used to solve data silos and privacy protection in machine learning, aiming to train global models together via multiple clients without sharing data. However, federated learning itself introduces certain security threats, which pose significant challenges in its practical applications. This article focuses on the common security risks of data poisoning during the training phase of federated learning clients. First, the definition of federated learning, attack types, data poisoning methods, privacy protection technology and data security situational awareness are summarized. Secondly, the system architecture fragility, communication efficiency shortcomings, computing resource consumption and situation prediction robustness of federated learning are analyzed, and related issues that affect the detection of data poisoning attacks are pointed out. Thirdly, a review is provided from the aspects of building a trusted federation, optimizing communication efficiency, improving computing power technology and personalized the federation. Finally, the research hotspots of the federated learning data poisoning attack situation prediction are prospected.

show abstract

Section: Build a Trusted Federated Learning Systemmentioning

confidence: 99%

Challenges and Countermeasures of Federated Learning Data Poisoning Attack Situation Prediction

Wu,

Jin,

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…The study deep leakage from gradients started the conversation for the reconstruction of data from model weights, since then studies like improved data leakage from gradients [23], PGSL [21], Industrial Private AI [5], and SPIN [7] were proposed that leverage model inversion attacks for specific applications. Following the trends, many studies considered derivatives of the aforementioned works to perform data or class label leakages from gradients such as WDLG [37], DEFEAT [38], and GLAUS [39].…”

Section: Model and Feature Inversionmentioning

confidence: 99%

Spike learning based Privacy Preservation of Internet of Medical Things in Metaverse

Khowaja,

Dahri,

Jarwar

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

With the rising trend of digital technologies, such as augmented and virtual reality, Metaverse has gained a notable popularity. The applications that will eventually benefit from Metaverse is the telemedicine and e-health fields. However, the data and techniques used for realizing the medical side of Metaverse is vulnerable to data and class leakage attacks. Most of the existing studies focus on either of the problems through encryption techniques or addition of noise. In addition, the use of encryption techniques affects the overall performance of the medical services, which hinders its realization. In this regard, we propose Generative adversarial networks and spike learning based convolutional neural network (GASCNN) for medical images that is resilient to both the data and class leakage attacks. We first propose the GANs for generating synthetic medical images from residual networks feature maps. We then perform a transformation paradigm to convert ResNet to spike neural networks (SNN) and use spike learning technique to encrypt model weights by representing the spatial domain data into temporal axis, thus making it difficult to be reconstructed. We conduct extensive experiments on publicly available MRI dataset and show that the proposed work is resilient to various data and class leakage attacks in comparison to existing state-of-the-art works (1.75x increase in FID score) with the exception of slightly decreased performance (less than 3%) from its ResNet counterpart. while achieving 52x energy efficiency gain with respect to standard ResNet architecture.

show abstract

Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges

Martínez Beltrán,

Pérez,

Sánchez

et al. 2023

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Decentralized Federated Learning: A Defense Against Gradient Inversion Attack

Cited by 4 publications

References 9 publications

Challenges and Countermeasures of Federated Learning Data Poisoning Attack Situation Prediction

Challenges and Countermeasures of Federated Learning Data Poisoning Attack Situation Prediction

Spike learning based Privacy Preservation of Internet of Medical Things in Metaverse

Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges

Contact Info

Product

Resources

About