GNNs are vulnerable to adversarial attacks that target both node features and graph structure, and their lack of interpretability remains a major obstacle to applying them to real world problems.
Source quote, verbatim
GNNs can be vulnerable to adversarial attacks on both node features and graph structure, and interpretability remains a major obstacle for applying GNNs to real-world problems.
From
Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024), Model Overview: Graph Neural Networks (GNNs), p. 23 https://ssrn.com/abstract=4855607 · source PDF
Cite as
Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024). SSRN: https://ssrn.com/abstract=4855607
Holds when
real world GNN deployments where adversaries can influence the graph
The quote above is an exact substring of the source PDF, whose sha256 is eb0b3e62374b45a8fa888c6bde9725e606bcb46cf4b5e74a6e851d9f25099113. Extraction method: pdf-text-layer. Attestation record: colloquium/attestations/621f4ef58b890c1c...json Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/4855607-011.md | sha256sum