CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918445881229312 |
|---|---|
| author | Wu, Yongxuan Lin, Xixun Zhang, He Sun, Nan Wang, Kun Zhou, Chuan Pan, Shirui Cao, Yanan |
| author_facet | Wu, Yongxuan Lin, Xixun Zhang, He Sun, Nan Wang, Kun Zhou, Chuan Pan, Shirui Cao, Yanan |
| contents | LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose Communication Inference Attack (CIA), a novel attack that constructs new adversarial queries to induce intermediate agents' reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12461 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems Wu, Yongxuan Lin, Xixun Zhang, He Sun, Nan Wang, Kun Zhou, Chuan Pan, Shirui Cao, Yanan Artificial Intelligence LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose Communication Inference Attack (CIA), a novel attack that constructs new adversarial queries to induce intermediate agents' reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS. |
| title | CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.12461 |