.png){kind=icon}
Return
DGGI: Deep Generative Gradient Inversion with diffusion model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2024.102620.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Federated learning is a privacy-preserving distributed framework that facilitates information fusion and sharing among different clients, enabling the training of a global model without exposing raw data. However, the gradient inversion attack that can reconstruct the training data via gradients has posed a significant threat. Prior attack approaches have demonstrated the efficacy of gradient inversion on low-resolution datasets with small batch sizes, which is impractical in real scenarios. To tackle this issue, this paper proposes an innovative and practical gradient inversion method, namely Deep Generative Gradient Inversion (DGGI), which employs the prior knowledge of diffusion models to enhance reconstruction performance on high-resolution datasets and larger batch sizes. Furthermore, a novel group consistency regularization term that constrains the distance between reconstruction and alignment images has been developed to address the issue of spatial variations caused by pre-trained diffusion model. Experiments conducted on both natural and medical image datasets demonstrate that our DGGI method outperforms state-of-the-art baselines in image reconstruction metrics. Furthermore, our approach achieves pixel-level reconstruction and causes leakage of privacy information, even at larger batch sizes or under various defenses, which can aid in the exploration of latent security concerns within information fusion models.
Keywords:
Gradient inversion
Computer privacy
Information security
Network security
Client data fusion
Journal
IF:
15.5
Papers:
4.2K
Citations:
2.7W
Organization
Cited Papers
ShareSaveDiff-IF: Multi-modality image fusion via diffusion model with fusion knowledge prior.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
ShareSavePrivacy protection in intelligent vehicle networking: A novel federated learning algorithm based on information fusionINFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
ShareSaveSurvey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challengesINFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAIShareSave
ShareSave
View more