Research map / Adversarial robustness and security / Attacks on text and graphs
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
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.
Studies label poisoning attacks on graph neural networks, examining pitfalls in how label-poisoning robustness is evaluated and proposing attacks on node labels.
Problem
Node labels used to train GNNs can be compromised by malicious users or noisy automated/crowd-sourced processes, and robustness to such adversarial label noise on graph data is under-studied.
Approach
Examines pitfalls in existing evaluation of label poisoning on graphs and develops label-poisoning attacks that target GNN training labels; the abstract is truncated so specifics are not stated.
Closest papers by meaning
- Clean-Label Graph Backdoor Attack in the Node Classification Task (AAAI 2025 · similarity 0.91)
- Exact Certification of (Graph) Neural Networks Against Label Poisoning (ICLR 2025 · similarity 0.90)
- Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending Against Poisoning Attacks (AAAI 2025 · similarity 0.88)
- Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.87)
- Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations (CVPR 2025 · similarity 0.87)
- If You Want to Be Robust, Be Wary of Initialization (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.