mlsanityData to 14 Oct 2026

PBM-VFL: Vertical Federated Learning with Feature and Sample Privacy

arXiv 2501.13916 ↗First posted 23 Jan 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present Poisson Binomial Mechanism Vertical Federated Learning (PBM-VFL), a communication-efficient Vertical Federated Learning algorithm with Differential Privacy guarantees. PBM-VFL combines Secure Multi-Party Computation with the recently introduced Poisson Binomial Mechanism to protect parties' private datasets during model training. We define the novel concept of feature privacy and analyze end-to-end feature and sample privacy of our algorithm. We compare sample privacy loss in VFL with privacy loss in HFL. We also provide the first theoretical characterization of the relationship between privacy budget, convergence error, and communication cost in differentially-private VFL. Finally, we empirically show that our model performs well with high levels of privacy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 23 Jan 2025.

Builds on

16 of 28 references.

References · 16

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  4. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  5. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  6. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  7. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  8. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
  9. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  10. 2018SGD and Hogwild! Convergence Without the Bounded Gradients Assumptioncited by 95
  11. 2020Vertically Federated Graph Neural Network for Privacy-Preserving Node Classificationcited by 61
  12. 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
4 more
  1. 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
  2. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 17
  3. 2022Differentially Private Vertical Federated Clusteringcited by 10
  4. 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6

Built on by

Not cited yet.