arXiv Machine Learning July 7, 2026 By Yi Lan, Ye Yuan

Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2607. 04091v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security risks.

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 Machine Learning.

arXiv Machine Learning

Jun 30

Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks

arXiv:2606. 29240v1 Announce Type: new Abstract: Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types.

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

benchmarks 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 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

arXiv AI

Sep 11

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.

By Yaning Jia, Shenyang Deng, Yaoqing Yang, Chiyu Ma, Wenxuan Xu, Soroush Vosoughi

safety

arXiv AI

4d ago

Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks

arXiv:2609.37972v1 Announce Type: cross Abstract: As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical...

By Ying Song, Xiaowei Jia, Balaji Palanisamy

benchmarks

One email a morning, machine-written

Related stories

Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks

Defending against Model Extraction for GNNs with Model Reprogramming

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

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

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

Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks