Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks

• URL: http://arxiv.org/abs/2506.13276v1
• Date: Mon, 16 Jun 2025 09:16:21 GMT
• Title: Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
• Abstract summary: This paper introduces ATAG-LLM, a novel black-box GIA framework tailored for text-attributed graphs (TAGs)<n>Our approach leverages large language models (LLMs) to generate interpretable text-level node attributes directly.<n>This method efficiently perturbs the target node with minimal training costs in a strict black-box setting, ensuring a text-level graph injection attack for TAGs.
• Score: 14.181622082567124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-attributed graphs (TAGs) integrate textual data with graph structures, providing valuable insights in applications such as social network analysis and recommendation systems. Graph Neural Networks (GNNs) effectively capture both topological structure and textual information in TAGs but are vulnerable to adversarial attacks. Existing graph injection attack (GIA) methods assume that attackers can directly manipulate the embedding layer, producing non-explainable node embeddings. Furthermore, the effectiveness of these attacks often relies on surrogate models with high training costs. Thus, this paper introduces ATAG-LLM, a novel black-box GIA framework tailored for TAGs. Our approach leverages large language models (LLMs) to generate interpretable text-level node attributes directly, ensuring attacks remain feasible in real-world scenarios. We design strategies for LLM prompting that balance exploration and reliability to guide text generation, and propose a similarity assessment method to evaluate attack text effectiveness in disrupting graph homophily. This method efficiently perturbs the target node with minimal training costs in a strict black-box setting, ensuring a text-level graph injection attack for TAGs. Experiments on real-world TAG datasets validate the superior performance of ATAG-LLM compared to state-of-the-art embedding-level and text-level attack methods.

Related papers

• Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning [63.602658976990874]
  Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks.<n>We present a retrieval-augmented view of GNNs: each layer makes predictions by applying anvariant to a node representation together with a permutation-in summary of retrieved graph context.<n>Motivated by this perspective, we propose RTA, a simple aggregation-based framework that replaces structural message passing with label-aware retrieval and propagation.
  arXiv  Detail & Related papers  (2026-08-27T07:25:44Z)
• Semi-Supervised Text-Attributed Graph Distillation [15.73558394941586]
  em Text-Attributed Graphs (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics.<n>We propose algo, a unified semi-supervised framework guided by the em Wasserstein Distance (WSD)
  arXiv  Detail & Related papers  (2026-05-27T14:52:24Z)
• Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs [22.41904611417485]
  Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node.<n>Recent advances leverage diverse backbones, such as graph neural networks (GNNs) and pre-trained language models (PLMs) to capture both structural and textual information in TAGs.<n>This diversity raises a key question: How can we design universal adversarial attacks that generalize across architectures to assess the security of TAG models?<n>We propose BadGraph, a novel attack framework that deeply elicits large language models (LLMs) understanding of general graph knowledge to jointly perturb both node topology and textual semantics
  arXiv  Detail & Related papers  (2026-03-22T10:15:22Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs [35.900360659024585]
  Interpretable Multi-Dimensional Graph Attack (IMDGA) is a novel human-centric adversarial attack framework for Graph-LLMs.<n>IMDGA demonstrates superior interpretability, attack effectiveness, stealthiness, and robustness compared to existing methods.<n>This work uncovers a previously underexplored semantic dimension of vulnerability in Graph-LLMs, offering valuable insights for improving their resilience.
  arXiv  Detail & Related papers  (2025-10-14T07:36:07Z)
• DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs [55.13817504780764]
  Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features, often rich in textual data, and graph structural information.<n>Graph-Enhanced LLMs emerge as a promising graph learning approach that converts graph information into prompts.<n>We propose Dual Granularity Prompting (DGP), which mitigates information overload by preserving fine-grained textual details for the target node.
  arXiv  Detail & Related papers  (2025-07-29T10:10:47Z)
• TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks [3.3238054848751535]
  We introduce TrustGLM, a comprehensive study evaluating the vulnerability of GraphLLMs to adversarial attacks across three dimensions: text, graph structure, and prompt manipulations.<n>Our findings reveal that GraphLLMs are highly susceptible to text attacks that merely replace a few semantically similar words in a node's textual attribute.<n>We also find that standard graph structure attack methods can significantly degrade model performance, while random shuffling of the candidate label set in prompt templates leads to substantial performance drops.
  arXiv  Detail & Related papers  (2025-06-13T14:48:01Z)
• Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment [24.0890725396281]
  We introduce GAGA, an efficient framework for TAG representation learning.<n>It reduces annotation time and cost by focusing on annotating only representative nodes and edges.<n>Experiments show that GAGA classification achieves accuracies on par with or surpassing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-08T14:34:29Z)
• Few-Shot Graph Out-of-Distribution Detection with LLMs [34.42512005781724]
  We propose a framework that combines the strengths of large language models (LLMs) and graph neural networks (GNNs) to enhance data efficiency in graph out-of-distribution (OOD) detection.<n>We show that LLM-GOOD significantly reduces human annotation costs and outperforms state-of-the-art baselines in terms of both ID classification accuracy and OOD detection performance.
  arXiv  Detail & Related papers  (2025-03-28T02:37:18Z)
• AHSG: Adversarial Attack on High-level Semantics in Graph Neural Networks [8.512355226572254]
  Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes.<n>Existing methods achieve attack stealthiness by constraining the modification budget and differences in graph properties.<n>We propose an Adversarial Attack on High-level Semantics for Graph Neural Networks (AHSG), which is a graph structure attack model that ensures the retention of primary semantics.
  arXiv  Detail & Related papers  (2024-12-10T12:35:37Z)
• SaVe-TAG: Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs [16.24571541782205]
  Real-world graph data often follows long-tailed distributions, making it difficult for Graph Neural Networks (GNNs) to generalize well across both head and tail classes.<n>Recent advances in Vicinal Risk Minimization (VRM) have shown promise in mitigating class imbalance with numeric semantics.
  arXiv  Detail & Related papers  (2024-10-22T10:36:15Z)
• Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks [50.19590901147213]
  Graph neural networks (GNNs) have become instrumental in diverse real-world applications, offering powerful graph learning capabilities. GNNs are vulnerable to adversarial attacks, including membership inference attacks (MIA) This paper proposes an effective two-stage defense, Graph Transductive Defense (GTD), tailored to graph transductive learning characteristics.
  arXiv  Detail & Related papers  (2024-06-12T06:36:37Z)
• Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level [21.003091265006102]
  Graph Neural Networks (GNNs) excel across various applications but remain vulnerable to adversarial attacks. In this paper, we pioneer the exploration of Graph Injection Attacks (GIAs) at the text level. We show that text interpretability, a factor previously overlooked at the embedding level, plays a crucial role in attack strength.
  arXiv  Detail & Related papers  (2024-05-26T02:12:02Z)
• Parameter-Efficient Tuning Large Language Models for Graph Representation Learning [62.26278815157628]
  We introduce Graph-aware. Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning. We use a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt. We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations.
  arXiv  Detail & Related papers  (2024-04-28T18:36:59Z)
• Everything Perturbed All at Once: Enabling Differentiable Graph Attacks [61.61327182050706]
  Graph neural networks (GNNs) have been shown to be vulnerable to adversarial attacks. We propose a novel attack method called Differentiable Graph Attack (DGA) to efficiently generate effective attacks. Compared to the state-of-the-art, DGA achieves nearly equivalent attack performance with 6 times less training time and 11 times smaller GPU memory footprint.
  arXiv  Detail & Related papers  (2023-08-29T20:14:42Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning [51.90524745663737]
  A key innovation is our use of explanations as features, which can be used to boost GNN performance on downstream tasks. Our method achieves state-of-the-art results on well-established TAG datasets. Our method significantly speeds up training, achieving a 2.88 times improvement over the closest baseline on ogbn-arxiv.
  arXiv  Detail & Related papers  (2023-05-31T03:18:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.