# kaal:claim:4855607-011

**Claim.** 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.

**Type.** failure  **Support.** evidenced

**Holds when.**

- real world GNN deployments where adversaries can influence the graph

**Source quote.**

> 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), page 23

**Cite as.** Wulf A. Kaal, How AI Models are Optimized Through Web3 Governance (2024). SSRN: https://ssrn.com/abstract=4855607

**Verify.** sha256 of source PDF `eb0b3e62374b45a8fa888c6bde9725e606bcb46cf4b5e74a6e851d9f25099113` at https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202024%20-%20How%20AI%20Models%20are%20Optimized%20Through%20Web3%20Governance.pdf

**Failure mode.** GNN adversarial vulnerability  (family: ai-model-and-training-failure)

**Topics.** ai-and-agents, citation-and-knowledge, consensus-and-security, research-methods

**Keywords.** graph-neural-networks, adversarial-attacks, interpretability, graph-structure, robustness

**Canonical form.** This markdown file is the canonical hashed representation of the claim. Its sha256 is the content hash used for attestation.