arXiv Machine Learning

GENIE: Watermarking Graph Neural Networks for Link Prediction

arXiv Machine Learning
6d ago

A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification

The paper introduces REMARK, a watermark‑based fingerprint framework designed to verify ownership of Graph Neural Networks (GNNs). REMARK generates in‑distribution watermark graphs that maximize output differences between GNN models, thereby reducing performance loss from out‑of‑distribution watermarks. It then extracts robust fingerprints from these output differences, eliminating the need for surrogate models trained on watermark data or reliance on specific output levels, and achieves state‑of‑the‑art verification accuracy across real‑world datasets and GNN architectures.

By Han Zhang, Yan Wang, Guanfeng Liu, Pengfei Ding, Huaxiong Wang, Kwok-Yan Lam
arXiv AI
2d ago

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
arXiv Machine Learning
Aug 27

Are LLM-Enhanced GNNs Privacy-Safe?

The paper evaluates privacy risks in graph neural networks enhanced by large language models (LLMs). Using a five‑stage framework, the authors test six real‑world text‑attributed graph datasets with 42 model configurations and six privacy attack methods across link, label, and membership inference threats. Results show that LLM‑enhanced GNNs are more vulnerable than shallow baselines, with semantic enrichment amplifying exploitable signals, and that differential privacy can reduce risk but at a significant cost to utility.

By Longzhu He, Zelang Wen, Chaozhuo Li, Sen Su
arXiv Machine Learning
Sep 2

MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks

MUGEN is a framework that generates unlearnable graph examples capable of protecting multiple downstream tasks—node classification, graph classification, and link prediction—simultaneously. It achieves this by perturbing a single clean dataset with a shared GNN encoder and task‑specific heads, guided by a Task‑Aligned Separability Objective (TASO) and a Type‑Adaptive Perturbation (TAP) that handles both discrete and continuous node attributes. Experiments on five benchmarks, four GNN backbones, and three learning paradigms show that MUGEN’s perturbations transfer across models and remain effective even under adversarial training and data augmentation.

By Ziyan Liu, Chengshuai Zhao, Huan Liu
arXiv Machine Learning
Jun 8

ADAGE: Active Defenses Against GNN Extraction

arXiv:2503. 00065v4 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, and recommendation systems.

By Jing Xu, Franziska Boenisch, Adam Dziedzic