paper-with-me

홈 › Papers

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

2025-06-16 · Yuefei Lyu, Chaozhuo Li, Xi Zhang, Tianle Zhang

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.

📄 PDF Abstract BibTeX arXiv:2506.13276

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation SystemsTAGText Generation

Similar Papers 제목 키워드 기반

Matryoshka: Learning to Drive Black-Box LLMs with LLMs

2024-10-28 · Changhao Li, Yuchen Zhuang, Rushi Qiang, Haotian Sun 외

Despite the impressive generative abilities of black-box large language models (LLMs), their inherent opacity hinders further advancements in capabilities such as reasoning, planning, and personalization. Existing works …

In-Context Learning

Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion

2023-12-21 · Nishtha Madaan, Srikanta Bedathur

Generating counterfactual explanations is one of the most effective approaches for uncovering the inner workings of black-box neural network models and building user trust. While remarkable strides have been made in gene…

counterfactualDiversity

Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors

2024-06-13 · Ying Zhou, Ben He, Le Sun

With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to concerns related to intellectual proper…

Data AugmentationText Detection

DALD: Improving Logits-based Detector without Logits from Black-box LLMs

2024-06-07 · Cong Zeng, Shengkun Tang, Xianjun Yang, Yuanzhou Chen 외

The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in…

Text DetectionText Generation

LLM-Generated Black-box Explanations Can Be Adversarially Helpful

2024-05-10 · Rohan Ajwani, Shashidhar Reddy Javaji, Frank Rudzicz, Zining Zhu

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and out…

Navigate