Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.12512 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917488106668032 |
|---|---|
| author | Bu, Haoran Zhang, Litian Zhang, Chuxuan Liu, Zhanyuan Pang, Hui Zhang, Xi |
| author_facet | Bu, Haoran Zhang, Litian Zhang, Chuxuan Liu, Zhanyuan Pang, Hui Zhang, Xi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12512 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents Bu, Haoran Zhang, Litian Zhang, Chuxuan Liu, Zhanyuan Pang, Hui Zhang, Xi Social and Information Networks Artificial Intelligence 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. |
| title | Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2605.12512 |