Privacy in Large Language Models: Attacks, Defenses and Future Directions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Haoran, Chen, Yulin, Luo, Jinglong, Wang, Jiecong, Peng, Hao, Kang, Yan, Zhang, Xiaojin, Hu, Qi, Chan, Chunkit, Xu, Zenglin, Hooi, Bryan, Song, Yangqiu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912050683314176
author Li, Haoran
Chen, Yulin
Luo, Jinglong
Wang, Jiecong
Peng, Hao
Kang, Yan
Zhang, Xiaojin
Hu, Qi
Chan, Chunkit
Xu, Zenglin
Hooi, Bryan
Song, Yangqiu
author_facet Li, Haoran
Chen, Yulin
Luo, Jinglong
Wang, Jiecong
Peng, Hao
Kang, Yan
Zhang, Xiaojin
Hu, Qi
Chan, Chunkit
Xu, Zenglin
Hooi, Bryan
Song, Yangqiu
contents The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on massive textual data, have brought unparalleled accessibility and usability for both models and users. On the other hand, unrestricted access to these models can also introduce potential malicious and unintentional privacy risks. Despite ongoing efforts to address the safety and privacy concerns associated with LLMs, the problem remains unresolved. In this paper, we provide a comprehensive analysis of the current privacy attacks targeting LLMs and categorize them according to the adversary's assumed capabilities to shed light on the potential vulnerabilities present in LLMs. Then, we present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks. Beyond existing works, we identify upcoming privacy concerns as LLMs evolve. Lastly, we point out several potential avenues for future exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2310_10383
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Privacy in Large Language Models: Attacks, Defenses and Future Directions
Li, Haoran
Chen, Yulin
Luo, Jinglong
Wang, Jiecong
Peng, Hao
Kang, Yan
Zhang, Xiaojin
Hu, Qi
Chan, Chunkit
Xu, Zenglin
Hooi, Bryan
Song, Yangqiu
Computation and Language
Cryptography and Security
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on massive textual data, have brought unparalleled accessibility and usability for both models and users. On the other hand, unrestricted access to these models can also introduce potential malicious and unintentional privacy risks. Despite ongoing efforts to address the safety and privacy concerns associated with LLMs, the problem remains unresolved. In this paper, we provide a comprehensive analysis of the current privacy attacks targeting LLMs and categorize them according to the adversary's assumed capabilities to shed light on the potential vulnerabilities present in LLMs. Then, we present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks. Beyond existing works, we identify upcoming privacy concerns as LLMs evolve. Lastly, we point out several potential avenues for future exploration.
title Privacy in Large Language Models: Attacks, Defenses and Future Directions
topic Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2310.10383