Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2411.09523 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909389568344064 |
|---|---|
| author | Gan, Yuyou Yang, Yong Ma, Zhe He, Ping Zeng, Rui Wang, Yiming Li, Qingming Zhou, Chunyi Li, Songze Wang, Ting Gao, Yunjun Wu, Yingcai Ji, Shouling |
| author_facet | Gan, Yuyou Yang, Yong Ma, Zhe He, Ping Zeng, Rui Wang, Yiming Li, Qingming Zhou, Chunyi Li, Songze Wang, Ting Gao, Yunjun Wu, Yingcai Ji, Shouling |
| contents | With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives.
To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09523 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents Gan, Yuyou Yang, Yong Ma, Zhe He, Ping Zeng, Rui Wang, Yiming Li, Qingming Zhou, Chunyi Li, Songze Wang, Ting Gao, Yunjun Wu, Yingcai Ji, Shouling Artificial Intelligence With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively. |
| title | Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2411.09523 |