arXiv Machine Learning
GENIE: Watermarking Graph Neural Networks for Link Prediction
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
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.
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.
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).
arXiv Machine Learning
Aug 26
GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
arXiv:2311.16139v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have become indispensable tools for learning from graph structured data, catering to various applications such a...
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.
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.