Attack and defense techniques in large language models: A survey and new perspectives
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908346030751744 |
|---|---|
| author | Liao, Zhiyu Chen, Kang Lin, Yuanguo Li, Kangkang Liu, Yunxuan Chen, Hefeng Huang, Xingwang Yu, Yuanhui |
| author_facet | Liao, Zhiyu Chen, Kang Lin, Yuanguo Li, Kangkang Liu, Yunxuan Chen, Hefeng Huang, Xingwang Yu, Yuanhui |
| contents | Large Language Models (LLMs) have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into adversarial prompt attack, optimized attacks, model theft, as well as attacks on application of LLMs, detailing their mechanisms and implications. Consequently, we analyze defense strategies, including prevention-based and detection-based defense methods. Although advances have been made, challenges remain to adapt to the dynamic threat landscape, balance usability with robustness, and address resource constraints in defense implementation. We highlight open problems, including the need for adaptive scalable defenses, explainable security techniques, and standardized evaluation frameworks. This survey provides actionable insights and directions for developing secure and resilient LLMs, emphasizing the importance of interdisciplinary collaboration and ethical considerations to mitigate risks in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attack and defense techniques in large language models: A survey and new perspectives Liao, Zhiyu Chen, Kang Lin, Yuanguo Li, Kangkang Liu, Yunxuan Chen, Hefeng Huang, Xingwang Yu, Yuanhui Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Large Language Models (LLMs) have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into adversarial prompt attack, optimized attacks, model theft, as well as attacks on application of LLMs, detailing their mechanisms and implications. Consequently, we analyze defense strategies, including prevention-based and detection-based defense methods. Although advances have been made, challenges remain to adapt to the dynamic threat landscape, balance usability with robustness, and address resource constraints in defense implementation. We highlight open problems, including the need for adaptive scalable defenses, explainable security techniques, and standardized evaluation frameworks. This survey provides actionable insights and directions for developing secure and resilient LLMs, emphasizing the importance of interdisciplinary collaboration and ethical considerations to mitigate risks in real-world applications. |
| title | Attack and defense techniques in large language models: A survey and new perspectives |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2505.00976 |