English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we measure the privacy leakage via studying whether graphrepresentations can be inverted to recover the graph used to generate them viagraph reconstruction attack (GRA). We propose a GRA that recovers a graph'sadjacency matrix from the representations via a graph decoder that minimizesthe 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 attentionnetwork (GAT), and our proposed simplicial neural network (SNN) via ahigher-order combinatorial Laplacian. Unlike the first two types ofrepresentations that only encode pairwise relationships, the third type ofrepresentation, i.e., SNN outputs, encodes higher-order interactions (e.g.,homological features) between nodes. We find that the SNN outputs reveal thelowest privacy-preserving ability to defend the GRA, followed by those of GATsand GCNs, which indicates the importance of building more privaterepresentations with higher-order node information that could defend thepotential threats, such as GRAs.

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