English

Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis

Cryptography and Security 2021-12-23 v2 Machine Learning Machine Learning

Abstract

Among existing privacy attacks on the gradient of neural networks, \emph{data reconstruction attack}, which reverse engineers the training batch from the gradient, poses a severe threat on the private training data. Despite its empirical success on large architectures and small training batches, unstable reconstruction accuracy is also observed when a smaller architecture or a larger batch is under attack. Due to the weak interpretability of existing learning-based attacks, there is little known on why, when and how data reconstruction attack is feasible. In our work, we perform the first analytic study on the security boundary of data reconstruction from gradient via a microcosmic view on neural networks with rectified linear units (ReLUs), the most popular activation function in practice. For the first time, we characterize the insecure/secure boundary of data reconstruction attack in terms of the \emph{neuron exclusivity state} of a training batch, indexed by the number of \emph{\textbf{Ex}clusively \textbf{A}ctivated \textbf{N}eurons} (ExANs, i.e., a ReLU activated by only one sample in a batch). Intuitively, we show a training batch with more ExANs are more vulnerable to data reconstruction attack and vice versa. On the one hand, we construct a novel deterministic attack algorithm which substantially outperforms previous attacks for reconstructing training batches lying in the insecure boundary of a neural network. Meanwhile, for training batches lying in the secure boundary, we prove the impossibility of unique reconstruction, based on which an exclusivity reduction strategy is devised to enlarge the secure boundary for mitigation purposes.

Keywords

Cite

@article{arxiv.2010.13356,
  title  = {Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis},
  author = {Xudong Pan and Mi Zhang and Yifan Yan and Jiaming Zhu and Min Yang},
  journal= {arXiv preprint arXiv:2010.13356},
  year   = {2021}
}

Comments

Accepted by USENIX Security'22; A preprint version

R2 v1 2026-06-23T19:38:32.633Z