AI Paper Atlas

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

Contrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning

Manshika C Bissessur, Melis Ilayda Bal, Michael Muehlebach

NeurIPS 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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

Proposes a contrastive adversarial training defense for graph neural networks against label poisoning attacks on training labels.

Problem

GNNs are vulnerable to label poisoning, where a few corrupted training labels propagate errors across the graph through message passing; existing defenses target label noise and rely on robust losses or heuristic cleaning.

Approach

Combines contrastive learning with adversarial training to make GNNs robust to label poisoning; the abstract is truncated so the specific mechanism beyond this framing is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace the contrastive detection model with a logit/loss-based node selection heuristic (ablation)CoLAT · Cora ML, 30% NTK poisoningtest accuracy gain over clean training: 0.4% gain vs 13% with detection modelHurt
Replace the contrastive detection model with a logit-based heuristic (ablation)CoLAT · Cora ML, SMultitest accuracy gain over clean training: about 5% vs up to 31%Hurt
Use adversarial iterative training instead of one-step label filtering with the detection model (ablation)CoLAT · Cora ML, 20% NTKtest accuracy gain over clean training: about 13% vs roughly 1% for filteringImproved
Use adversarial iterative training instead of one-step label filtering (ablation)CoLAT · Cora ML, 20% SMultitest accuracy gain over clean training: around 26% vs about 8%Improved
Select the most inconsistent nodes rather than the most consistent nodes (ablation)CoLAT · Cora ML, NTK and SMultitest accuracy: 0.4978 -> 0.6689 (NTK 20%)Improved
Apply CoLAT with GraphSAGE backboneCoLAT · Cora ML, SMulti 30%test accuracy gain: up to 31% gain at 30% poisoningImproved
Update the detection model less often (interval 1, 5, 10, 20) (ablation)CoLAT · OGBN-ArXivtest accuracy and training timeImproved
Apply CoLAT on clean labelsGCN · Cora ML, clean labelstest accuracy: 0.8270 -> 0.8377Improved
Apply CoLAT on a heterophilic graphGCN · Actor, NTK low poisoningtest accuracyNo clear effect
Apply CoLAT on a heterophilic graph under SMultiGCN · Actor, SMulti 30%test accuracy: 0.1079 -> 0.1444Improved
Apply CoLAT on Citeseer under SMulti 20%GCN · Citeseer, SMulti 20%test accuracy: 0.6167 -> 0.6200No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy