Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2505.08830 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916735659016192 |
|---|---|
| author | Jiang, Wenhao Luo, Yuchuan Deng, Guilin Chen, Silong Yang, Xu Wu, Shihong Gao, Xinwen Liu, Lin Fu, Shaojing |
| author_facet | Jiang, Wenhao Luo, Yuchuan Deng, Guilin Chen, Silong Yang, Xu Wu, Shihong Gao, Xinwen Liu, Lin Fu, Shaojing |
| contents | The integration of Large Language Models (LLMs) and Federated Learning (FL) presents a promising solution for joint training on distributed data while preserving privacy and addressing data silo issues. However, this emerging field, known as Federated Large Language Models (FLLM), faces significant challenges, including communication and computation overheads, heterogeneity, privacy and security concerns. Current research has primarily focused on the feasibility of FLLM, but future trends are expected to emphasize enhancing system robustness and security. This paper provides a comprehensive review of the latest advancements in FLLM, examining challenges from four critical perspectives: feasibility, robustness, security, and future directions. We present an exhaustive survey of existing studies on FLLM feasibility, introduce methods to enhance robustness in the face of resource, data, and task heterogeneity, and analyze novel risks associated with this integration, including privacy threats and security challenges. We also review the latest developments in defense mechanisms and explore promising future research directions, such as few-shot learning, machine unlearning, and IP protection. This survey highlights the pressing need for further research to enhance system robustness and security while addressing the unique challenges posed by the integration of FL and LLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08830 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Large Language Models: Feasibility, Robustness, Security and Future Directions Jiang, Wenhao Luo, Yuchuan Deng, Guilin Chen, Silong Yang, Xu Wu, Shihong Gao, Xinwen Liu, Lin Fu, Shaojing Cryptography and Security Artificial Intelligence The integration of Large Language Models (LLMs) and Federated Learning (FL) presents a promising solution for joint training on distributed data while preserving privacy and addressing data silo issues. However, this emerging field, known as Federated Large Language Models (FLLM), faces significant challenges, including communication and computation overheads, heterogeneity, privacy and security concerns. Current research has primarily focused on the feasibility of FLLM, but future trends are expected to emphasize enhancing system robustness and security. This paper provides a comprehensive review of the latest advancements in FLLM, examining challenges from four critical perspectives: feasibility, robustness, security, and future directions. We present an exhaustive survey of existing studies on FLLM feasibility, introduce methods to enhance robustness in the face of resource, data, and task heterogeneity, and analyze novel risks associated with this integration, including privacy threats and security challenges. We also review the latest developments in defense mechanisms and explore promising future research directions, such as few-shot learning, machine unlearning, and IP protection. This survey highlights the pressing need for further research to enhance system robustness and security while addressing the unique challenges posed by the integration of FL and LLM. |
| title | Federated Large Language Models: Feasibility, Robustness, Security and Future Directions |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2505.08830 |