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

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

URL: http://arxiv.org/abs/2310.10383v2
Date: Mon, 30 Sep 2024 11:58:27 GMT
Title: Privacy in Large Language Models: Attacks, Defenses and Future Directions
Authors: Haoran Li, Yulin Chen, Jinglong Luo, Jiecong Wang, Hao Peng, Yan Kang, Xiaojin Zhang, Qi Hu, Chunkit Chan, Zenglin Xu, Bryan Hooi, Yangqiu Song,
Abstract summary: We analyze the current privacy attacks targeting large language models (LLMs) and categorize them according to the adversary's assumed capabilities. We present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks.
Score: 84.73301039987128
License:
Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.