Research map / Adversarial robustness and security / Attacks on text and graphs

Mitigating Emergent Robustness Degradation while Scaling Graph Learning

ICLR 2024 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

The paper studies robustness of graph neural networks against adversarial attacks as they scale, addressing emergent robustness degradation in graph learning.

Problem

Graph neural networks are vulnerable to adversarial attacks, and existing defenses struggle to avoid major limitations, including an emergent robustness degradation problem when scaling.

Approach

Not stated in the provided abstract; the abstract is truncated before the proposed method is described.

Closest papers by meaning

• Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks (ICLR 2024 · similarity 0.90)
• Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.90)
• A Simple and Yet Fairly Effective Defense for Graph Neural Networks (AAAI 2024 · similarity 0.90)
• If You Want to Be Robust, Be Wary of Initialization (NeurIPS 2024 · similarity 0.89)
• Robust Graph Condensation via Classification Complexity Mitigation (NeurIPS 2025 · similarity 0.89)
• Robust Graph Neural Networks via Unbiased Aggregation (NeurIPS 2024 · similarity 0.89)