• shareshare
  • link
  • cite
  • add
auto_awesome_motion View all 2 versions
Publication . Conference object . Contribution for newspaper or weekly magazine . 2021

On the Privacy of Federated Pipelines

Reza Nasirigerdeh; Reihaneh Torkzadehmahani; Jan Baumbach; David Blumenthal;
Closed Access
Published: 11 Jul 2021
Publisher: Association for Computing Machinery
Country: Denmark

Federated learning (FL) is becoming an increasingly popular machine learning paradigm in application scenarios where sensitive data available at various local sites cannot be shared due to privacy protection regulations. In FL, the sensitive data never leaves the local sites and only model parameters are shared with a global aggregator. Nonetheless, it has recently been shown that, under some circumstances, the private data can be reconstructed from the model parameters, which implies that data leakage can occur in FL. In this paper, we draw attention to another risk associated with FL: Even if federated algorithms are individually privacy-preserving, combining them into pipelines is not necessarily privacy-preserving. We provide a concrete example from genome-wide association studies, where the combination of federated principal component analysis and federated linear regression allows the aggregator to retrieve sensitive patient data by solving an instance of the multidimensional subset sum problem. This supports the increasing awareness in the field that, for FL to be truly privacy-preserving, measures have to be undertaken to protect against data leakage at the aggregator.

Subjects by Vocabulary

Microsoft Academic Graph classification: Computer science Computer security computer.software_genre computer Subset sum problem Field (computer science) Integer programming Privacy protection Federated learning News aggregator Pipeline transport Leakage (economics)


federated learning, genome-wide association studies, integer linear programming, multidimensional subset sum, privacy

Related Organizations
Related to Research communities
Download fromView all 2 sources