arXiv AI October 28, 2026 By Vincess Dongmo, Astride Melvin Fokam Ninyim

When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning

The paper investigates when it is better to ignore a relation in multi-relational graph learning rather than use it, taking into account the varying manipulation costs an adversary faces. It shows that a degree‑gating strategy outperforms any selection or reweighting when a subset of the population is isolated on a relation and the attacker cannot open the gate, and that a per‑node exposure bound can identify which relation to harden. The authors provide theoretical guarantees, empirical validation on real and synthetic graphs, and a selection protocol that is never significantly worse than ignoring the graph.

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.

arXiv Machine Learning

Jul 9

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints

arXiv:2607. 07089v1 Announce Type: new Abstract: Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction.

By Alan Gany, Bogdan Cautis, Silviu Maniu

benchmarks safety

arXiv Machine Learning

Sep 30

Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphs

arXiv:2609.37667v1 Announce Type: new Abstract: Counterfactual explanations for graph neural networks (GNNs) find the minimal intervention that flips a node's prediction--but computing one requires r...

By Yuxiang Yao, Zijun Zhao

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

Hugging Face Trending Papers

Jul 8

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints

Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction. We study the adversarial robustness of this pipeline.

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 AI

2d ago

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

arXiv:2605.12827v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) deployed as cloud services can be *stolen* through *model-extraction attacks*, which train a surrogate from quer...

By Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty, Yushun Dong

benchmarks

One email a morning, machine-written

Related stories

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints

Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphs

The Confidence Trap: Calibration Attacks for Graph Neural Networks

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints

Defending against Model Extraction for GNNs with Model Reprogramming

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?