A Survey on Privacy Risks and Protection in Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915272889204736 |
|---|---|
| author | Chen, Kang Zhou, Xiuze Lin, Yuanguo Feng, Shibo Shen, Li Wu, Pengcheng |
| author_facet | Chen, Kang Zhou, Xiuze Lin, Yuanguo Feng, Shibo Shen, Li Wu, Pengcheng |
| contents | Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized extraction of training data and the potential exploitation of these vulnerabilities by malicious actors. Next, we review existing privacy protection against such risks, such as inference detection, federated learning, backdoor mitigation, and confidential computing, and assess their effectiveness in preventing privacy leakage. Furthermore, we highlight key practical challenges and propose future research directions to develop secure and privacy-preserving LLMs, emphasizing privacy risk assessment, secure knowledge transfer between models, and interdisciplinary frameworks for privacy governance. Ultimately, this survey aims to establish a roadmap for addressing escalating privacy challenges in the LLMs domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Privacy Risks and Protection in Large Language Models Chen, Kang Zhou, Xiuze Lin, Yuanguo Feng, Shibo Shen, Li Wu, Pengcheng Cryptography and Security Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized extraction of training data and the potential exploitation of these vulnerabilities by malicious actors. Next, we review existing privacy protection against such risks, such as inference detection, federated learning, backdoor mitigation, and confidential computing, and assess their effectiveness in preventing privacy leakage. Furthermore, we highlight key practical challenges and propose future research directions to develop secure and privacy-preserving LLMs, emphasizing privacy risk assessment, secure knowledge transfer between models, and interdisciplinary frameworks for privacy governance. Ultimately, this survey aims to establish a roadmap for addressing escalating privacy challenges in the LLMs domain. |
| title | A Survey on Privacy Risks and Protection in Large Language Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2505.01976 |