# Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?

arXiv: https://arxiv.org/abs/2408.08685 · HTML: https://mlsanity.com/paper/2408.08685/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 64 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Adversarial Attack and Defense on Graph Data: A Survey](https://mlsanity.com/paper/1812.10528/) (2018)
- [Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning](https://mlsanity.com/paper/2305.19523/) (2023)
- [Node Similarity Preserving Graph Convolutional Networks](https://mlsanity.com/paper/2011.09643/) (2020)
- [DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses](https://mlsanity.com/paper/2005.06149/) (2020)
- [A Review on Graph Neural Network Methods in Financial Applications](https://mlsanity.com/paper/2111.15367/) (2021)
- [Hiding Individuals and Communities in a Social Network](https://mlsanity.com/paper/1608.00375/) (2016)
- [Label-free Node Classification on Graphs with Large Language Models (LLMS)](https://mlsanity.com/paper/2310.04668/) (2023)
- [GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning](https://mlsanity.com/paper/2306.13089/) (2023)
- [GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks](https://mlsanity.com/paper/2402.07197/) (2024)
- [Are Defenses for Graph Neural Networks Robust?](https://mlsanity.com/paper/2301.13694/) (2023)
- [Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN](https://mlsanity.com/paper/2207.00012/) (2022)

## Built on by (most cited first, 23 of 23)

- [GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments](https://mlsanity.com/paper/2504.00711/) (2025)
- [Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning](https://mlsanity.com/paper/2603.01385/) (2026)
- [Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge](https://mlsanity.com/paper/2504.19730/) (2025)
- [Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?](https://mlsanity.com/paper/2603.26105/) (2026)
- [Incomplete Graph Learning: A Comprehensive Survey](https://mlsanity.com/paper/2502.12412/) (2025)
- [Graph Tokenization for Bridging Graphs and Transformers](https://mlsanity.com/paper/2603.11099/) (2026)
- [CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?](https://mlsanity.com/paper/2512.11352/) (2025)
- [Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding](https://mlsanity.com/paper/2605.03514/) (2026)
- [Trustworthy GNNs with LLMs: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2502.08353/) (2025)
- [Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses](https://mlsanity.com/paper/2510.17185/) (2025)
- [Bridging Semantic Understanding and Popularity Bias with LLMs](https://mlsanity.com/paper/2601.09478/) (2026)
- [DRGW: Learning Disentangled Representations for Robust Graph Watermarking](https://mlsanity.com/paper/2601.13569/) (2026)
- [Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval](https://mlsanity.com/paper/2604.15951/) (2026)
- [Composable Crystals: Controllable Materials Discovery via Concept Learning](https://mlsanity.com/paper/2605.14769/) (2026)
- [Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks](https://mlsanity.com/paper/2506.13276/) (2025)
- [Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis](https://mlsanity.com/paper/2506.20806/) (2025)
- [Towards Pre-trained Graph Condensation via Optimal Transport](https://mlsanity.com/paper/2509.14722/) (2025)
- [When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach](https://mlsanity.com/paper/2510.08952/) (2025)
- [DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs](https://mlsanity.com/paper/2601.16519/) (2026)
- [Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2601.21978/) (2026)
- [AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation](https://mlsanity.com/paper/2602.17071/) (2026)
- [TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection](https://mlsanity.com/paper/2605.19738/) (2026)
- [Riemannian Graph Tokenizer for Structural Knowledge Transfer](https://mlsanity.com/paper/2610.15427/) (2026)

## Abstract (arXiv)

Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention. Recently, we have witnessed the significant success of large language models (LLMs), leading many to explore the great potential of LLMs on GNNs. However, they mainly focus on improving the performance of GNNs by utilizing LLMs to enhance the node features. Therefore, we ask: Will the robustness of GNNs also be enhanced with the powerful understanding and inference capabilities of LLMs? By presenting the empirical results, we find that despite that LLMs can improve the robustness of GNNs, there is still an average decrease of 23.1% in accuracy, implying that the GNNs remain extremely vulnerable against topology attacks. Therefore, another question is how to extend the capabilities of LLMs on graph adversarial robustness. In this paper, we propose an LLM-based robust graph structure inference framework, LLM4RGNN, which distills the inference capabilities of GPT-4 into a local LLM for identifying malicious edges and an LM-based edge predictor for finding missing important edges, so as to recover a robust graph structure. Extensive experiments demonstrate that LLM4RGNN consistently improves the robustness across various GNNs. Even in some cases where the perturbation ratio increases to 40%, the accuracy of GNNs is still better than that on the clean graph. The source code can be found in https://github.com/zhongjian-zhang/LLM4RGNN.