AI RESEARCH

Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?

arXiv CS.LG

ArXi:2603.26105v1 Announce Type: new Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features, giving rise to LLM-enhanced GNNs that achieve notable performance gains. However, the robustness of these models against poisoning attacks, which manipulate both graph structures and textual attributes during