arXiv (All)
open access
A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks
Adversarial attacks on graph neural networks (GNNs) have been studied as a model-centric optimization problem driven by gradients, learned policies, or meta-learning, with the graph treated as a passive substrate. This view overlooks a defining feature of GNNs: their predictions are produced by stru
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks#996526
- ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale#405554
- A Distribution-Free Separation Between Learned and Fixed Features#1400165
- A Model-Independent Trojan Attack on Deep Learning-Based FDIA Detection in Smart Grid Protection Systems.#489725
- Residual Transferability in Neural Image Watermarking#1116572
Record · ID 1488919
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive