让聊天机器人学会构建类人社交网络，骗过检测系统。
Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents
- 用图结构增强LLM，让机器人理解全局社交关系。
- 新生成的机器人网络使现有检测模型准确率下降超过40%。
- 适合研究社交机器人检测与防御的学者参考。
受大型语言模型（LLMs）驱动的社会机器人可自主进行局部互动，其类人行为使其能逃避社交机器人检测。然而，尽管这些机器人表现出真实的局部社交互动，却无法保持类人的社交网络结构。这是因为基于LLM的机器人缺乏图感知能力，无法在全局交互中协调，导致其容易被图神经网络（GNN）-based检测方法识别。为解决此问题，我们提出GraphMind，使LLM驱动的社交机器人能够显式学习并拟合类人社交网络结构。在此基础上，我们进一步构建了GraphMind-Botnet，一个用于评估现有社交机器人检测算法性能的LLM驱动机器人网络。在基于GraphMind-Botnet生成的数据集上进行实验，结果显示，文本型和图型检测模型的区分能力均显著下降。结果凸显了社交链路构建在LLM驱动社交网络生成中的关键作用，同时暴露了现有机器人检测机制的根本缺陷。
原文摘要 · Abstract (English)
Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade social bot detection. However, while these botnets exhibit realistic local social interactions, they fail to preserve human-like social network. This is because LLM-based bots are graph-unaware and cannot coordinate over global interactions, which makes those botnets vulnerable to graph neural network (GNN)-based detection. To address this limitation, we propose GraphMind, which equips LLM-driven social bots to explicitly learn and fit human-like social network structures. Building on this foundation, we further construct GraphMind-Botnet, a LLM-driven botnet designed to evaluate the performance of existing social bot detection algorithms. Experiments on datasets derived from GraphMind-Botnet show that both text-based and graph-based detection models show substantially degraded performance in distinguishing. Our results highlight the critical role of social link construction in LLM-driven social network generation, while exposing fundamental weaknesses in existing bot detection mechanisms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。