arXiv AI August 18, 2026 By Ziluowen Luo, Jun Yin, Ruochen Liu, Ming Cheng, Shirui Pan, Chengqi Zhang, Senzhang Wang

NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption

arXiv:2608. 16038v1 Announce Type: cross Abstract: Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried predictions to perturbed inputs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv Machine Learning

Jun 5

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

arXiv:2606. 05756v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable performance across a range of applications involving graph-structured data, particularly in high-stakes domains.

By Jialiang Yin, Zheng Zhao, Linsey Pang, Bo Dong, Bin Shi, Jiaxing Zhang

benchmarks

arXiv AI

Jun 2

Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It

arXiv:2605. 07527v2 Announce Type: replace-cross Abstract: Recent work has observed that explanations produced by Self-Interpretable Graph Neural Networks (SI-GNNs) can be self-inconsistent: when the model is reapplied to its own explanatory graph subset, it may produce a different explanation.

By Wenxin Tai, Yaqian Liu, Ting Zhong, Fan Zhou

benchmarks

arXiv AI

Jul 20

AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing

arXiv:2503. 22998v2 Announce Type: replace-cross Abstract: Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness.

By Yuni Lai, Yulin Zhu, Yixuan Sun, Yulun Wu, Bin Xiao, Gaolei Li, Jianhua Li, Qi Xie, Kai Zhou

data-engineering

arXiv Machine Learning

Jul 31

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

arXiv:2607. 28185v1 Announce Type: new Abstract: Oversmoothing is a fundamental limitation of deep graph neural networks (GNNs), where repeated message passing causes node representations to become increasingly similar, eventually collapsing toward a low-dimensional subspace.

By Mostafa Haghir Chehreghani

arXiv AI

Jun 9

The Confidence Trap: Calibration Attacks for Graph Neural Networks

arXiv:2606. 08467v1 Announce Type: cross Abstract: While confidence calibration is essential for trustworthy decision-making in safety-critical applications, the robustness of calibrated GNNs to adversarial structural perturbations remains largely unexplored.

By Cuong Dang, Jiahao Zhang, Hieu Ta Quang, Dung Le, Lu Cheng, Suhang Wang

rag safety

arXiv AI

Jul 23

AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

arXiv:2602. 17071v3 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies.

By Rong Fu, Muge Qi, Chunlei Meng, Shuo Yin, Kun Liu, Simon Fong

llms safety

One email a morning, machine-written

Related stories

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It

AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

The Confidence Trap: Calibration Attacks for Graph Neural Networks

AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation