Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning

Research output: Chapter in Book/Entry/PoemConference contribution

Abstract

Federated learning (FL) aims at keeping client data local to preserve privacy. Instead of gathering the data itself, the server only collects aggregated gradient updates from clients. Following the popularity of FL, there has been considerable amount of work revealing the vulnerability of FL approaches by reconstructing the input data from gradient updates. Yet, most existing works assume an FL setting with unrealistically small batch size, and have poor image quality when the batch size is large. Other works modify the neural network architectures or parameters to the point of being suspicious, and thus, can be detected by clients. Moreover, most of them can only reconstruct one sample input from a large batch. To address these limitations, we propose a novel and analytical approach, referred to as the maximum knowledge orthogonality reconstruction (MKOR), to reconstruct clients' data. Our proposed method reconstructs a mathematically proven high-quality image from large batches. MKOR only requires the server to send secretly modified parameters to clients and can efficiently and inconspicuously reconstruct images from clients' gradient updates. We evaluate MKOR's performance on MNIST, CIFAR-100, and ImageNet datasets and compare it with the state-of-the-art baselines. The results show that MKOR outperforms the existing approaches, and draw attention to a pressing need for further research on the privacy protection of FL so that comprehensive defense approaches can be developed. The code is available at: https://github.com/wfwf10/MKOR.

Original languageEnglish (US)
Title of host publicationProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3872-3881
Number of pages10
ISBN (Electronic)9798350318920
DOIs
StatePublished - 2024
Event2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 - Waikoloa, United States
Duration: Jan 4 2024Jan 8 2024

Publication series

NameProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024

Conference

Conference2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Country/TerritoryUnited States
CityWaikoloa
Period1/4/241/8/24

Keywords

  • Adversarial learning
  • Algorithms
  • Algorithms
  • Explainable
  • accountable
  • adversarial attack and defense methods
  • ethical computer vision
  • fair
  • privacy-preserving

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning'. Together they form a unique fingerprint.

Cite this