ExPLoit: Extracting Private Labels in Split Learning

Sanjay Kariyappa; Moinuddin K Qureshi

ExPLoit: Extracting Private Labels in Split Learning

Cryptography and Security 2022-04-15 v2 Artificial Intelligence Machine Learning

Authors: Sanjay Kariyappa , Moinuddin K Qureshi

Abstract

Split learning is a popular technique used for vertical federated learning (VFL), where the goal is to jointly train a model on the private input and label data held by two parties. This technique uses a split-model, trained end-to-end, by exchanging the intermediate representations (IR) of the inputs and gradients of the IR between the two parties. We propose ExPLoit - a label-leakage attack that allows an adversarial input-owner to extract the private labels of the label-owner during split-learning. ExPLoit frames the attack as a supervised learning problem by using a novel loss function that combines gradient-matching and several regularization terms developed using key properties of the dataset and models. Our evaluations show that ExPLoit can uncover the private labels with near-perfect accuracy of up to 99.96%. Our findings underscore the need for better training techniques for VFL.

Keywords

privacy attacks on machine learning differential privacy

Cite

@article{arxiv.2112.01299,
  title  = {ExPLoit: Extracting Private Labels in Split Learning},
  author = {Sanjay Kariyappa and Moinuddin K Qureshi},
  journal= {arXiv preprint arXiv:2112.01299},
  year   = {2022}
}

ExPLoit: Extracting Private Labels in Split Learning

Abstract

Keywords

Cite

Related papers