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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Graph Neural Networks (GNNs) have achieved promising performance in variousreal-world applications. Building a powerful GNN model is not a trivial task,as it requires a large amount of training data, powerful computing resources,and human expertise in fine-tuning the model. Moreover, with the development ofadversarial attacks, e.g., model stealing attacks, GNNs raise challenges tomodel authentication. To avoid copyright infringement on GNNs, verifying theownership of the GNN models is necessary.  This paper presents a watermarking framework for GNNs for both graph and nodeclassification tasks. We 1) design two strategies to generate watermarked datafor the graph classification task and one for the node classification task, 2)embed the watermark into the host model through training to obtain thewatermarked GNN model, and 3) verify the ownership of the suspicious model in ablack-box setting. The experiments show that our framework can verify theownership of GNN models with a very high probability (up to $99\%$) for bothtasks. Finally, we experimentally show that our watermarking approach is robustagainst a state-of-the-art model extraction technique and four state-of-the-artdefenses against backdoor attacks.

Watermarking Graph Neural Networks based on Backdoor Attacks