DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914916398530560 |
|---|---|
| author | Sun, Xiongtao Liu, Gan He, Zhipeng Li, Hui Li, Xiaoguang |
| author_facet | Sun, Xiongtao Liu, Gan He, Zhipeng Li, Hui Li, Xiaoguang |
| contents | Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts, which inevitably pose significant risks of personal identifiable information (PII) leakage. Therefore, this paper proposes DePrompt, a desensitization protection and effectiveness evaluation framework for prompt, enabling users to safely and transparently utilize LLMs. Specifically, by leveraging large model fine-tuning techniques as the underlying privacy protection method, we integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Additionally, through the analysis of key features in prompt desensitization scenarios, we devise adversarial generative desensitization methods that retain important semantic content while disrupting the link between identifiers and privacy attributes. Furthermore, we present utility evaluation metrics for prompt to better gauge and balance privacy and usability. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios. Through comparison with benchmarks and other model methods, experimental evaluations demonstrate that our desensitized prompt exhibit superior privacy protection utility and model inference results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08930 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts Sun, Xiongtao Liu, Gan He, Zhipeng Li, Hui Li, Xiaoguang Cryptography and Security Artificial Intelligence Computation and Language Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts, which inevitably pose significant risks of personal identifiable information (PII) leakage. Therefore, this paper proposes DePrompt, a desensitization protection and effectiveness evaluation framework for prompt, enabling users to safely and transparently utilize LLMs. Specifically, by leveraging large model fine-tuning techniques as the underlying privacy protection method, we integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Additionally, through the analysis of key features in prompt desensitization scenarios, we devise adversarial generative desensitization methods that retain important semantic content while disrupting the link between identifiers and privacy attributes. Furthermore, we present utility evaluation metrics for prompt to better gauge and balance privacy and usability. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios. Through comparison with benchmarks and other model methods, experimental evaluations demonstrate that our desensitized prompt exhibit superior privacy protection utility and model inference results. |
| title | DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2408.08930 |