# Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract)

arXiv: https://arxiv.org/abs/2302.04373 · HTML: https://mlsanity.com/paper/2302.04373/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 8 references that are in the map.
- First posted on arXiv 8 Feb 2023.

## Builds on (most cited first, 4 of 4)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Stealing Links from Graph Neural Networks](https://mlsanity.com/paper/2005.02131/) (2020)

## Built on by (most cited first, 4 of 4)

- [Shared and Private Information Learning in Multimodal Sentiment Analysis with Deep Modal Alignment and Self-supervised Multi-Task Learning](https://mlsanity.com/paper/2305.08473/) (2023)
- [Part-Attention Based Model Make Occluded Person Re-Identification Stronger](https://mlsanity.com/paper/2404.03443/) (2024)
- [Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark](https://mlsanity.com/paper/2603.14756/) (2026)
- [Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes](https://mlsanity.com/paper/2302.04383/) (2023)

## Abstract (arXiv)

In this paper, we measure the privacy leakage via studying whether graph representations can be inverted to recover the graph used to generate them via graph reconstruction attack (GRA). We propose a GRA that recovers a graph's adjacency matrix from the representations via a graph decoder that minimizes the reconstruction loss between the partial graph and the reconstructed graph. We study three types of representations that are trained on the graph, i.e., representations output from graph convolutional network (GCN), graph attention network (GAT), and our proposed simplicial neural network (SNN) via a higher-order combinatorial Laplacian. Unlike the first two types of representations that only encode pairwise relationships, the third type of representation, i.e., SNN outputs, encodes higher-order interactions (e.g., homological features) between nodes. We find that the SNN outputs reveal the lowest privacy-preserving ability to defend the GRA, followed by those of GATs and GCNs, which indicates the importance of building more private representations with higher-order node information that could defend the potential threats, such as GRAs.