arXiv AI September 11, 2026 By Yaning Jia, Shenyang Deng, Yaoqing Yang, Chiyu Ma, Wenxuan Xu, Soroush Vosoughi

Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks

Kernel-Complexity Edge Sanitization (KCES) is a training‑free, model‑agnostic defense for Graph Neural Networks that identifies and removes edges with high Kernel‑Complexity (KC) scores, which are indicative of structural influence on the graph kernel complexity metric. KCES leverages a theoretical upper bound on GNN test error derived from the graph Gram matrix to compute edge‑specific KC scores, pruning edges that are empirically enriched with adversarial perturbations. The method is computationally efficient, scalable to large graphs, and consistently outperforms representative robust baselines across diverse attack settings without requiring retraining.

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.

safety

arXiv Machine Learning

Aug 13

Defending against Model Extraction for GNNs with Model Reprogramming

arXiv:2608. 11495v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS).

By Yan Wen, Zhenyi Wang, Heng Huang

safety

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 Machine Learning

Oct 15

Blackknife: Query-Free Black-Box Rewiring Attacks on Heterogeneous Graph Neural Networks

Blackknife is a query‑free, strict black‑box evasion attack designed for heterogeneous graph neural networks (HGNNs). It relies solely on observing one‑hop structures, ground‑truth labels, and raw features of target nodes, without using victim‑model outputs. The attack trains a shared surrogate on observable edges and relation types, then optimizes structural perturbations via continuous relaxation and projected gradient ascent, preserving node degrees while adding a cosine‑similarity penalty and adaptive structural classifier for regularization. Experiments show competitive success rates across multiple victim architectures and defense settings, revealing HGNN vulnerabilities under restricted graph access and query‑free attack generation.

By Honglin Gao, Junhao Ren, Lan Zhao, Yue Yang, Peilin Du, Jindong Chang, Gaoxi Xiao

arXiv AI

Jun 30

Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

arXiv:2606. 29748v1 Announce Type: new Abstract: The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive.

By Adebayo Keji, Sayanton Dibbo

rag benchmarks safety

arXiv Machine Learning

Jun 10

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

arXiv:2502. 01272v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks.

By Chang Liu, Hai Huang, Yujie Xing, Xingquan Zuo

rag

arXiv AI

Sep 1

Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL

arXiv:2608.29054v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly i...

By Shuomin Xue, Jingyuan Li, Ju Jia, Jingxuan Yu, Xiaojun Jia

multimodal benchmarks safety

One email a morning, machine-written

Related stories

Defending against Model Extraction for GNNs with Model Reprogramming

The Confidence Trap: Calibration Attacks for Graph Neural Networks

Blackknife: Query-Free Black-Box Rewiring Attacks on Heterogeneous Graph Neural Networks

Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL