Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912198181257216 |
|---|---|
| author | Asthana, Shubhi Zhang, Bing Mahindru, Ruchi DeLuca, Chad Gentile, Anna Lisa Gopisetty, Sandeep |
| author_facet | Asthana, Shubhi Zhang, Bing Mahindru, Ruchi DeLuca, Chad Gentile, Anna Lisa Gopisetty, Sandeep |
| contents | The adoption of Large Language Models (LLMs) has revolutionized AI applications but poses significant challenges in safeguarding user privacy. Ensuring compliance with privacy regulations such as GDPR and CCPA while addressing nuanced privacy risks requires robust and scalable frameworks. This paper presents a detailed study of OneShield Privacy Guard, a framework designed to mitigate privacy risks in user inputs and LLM outputs across enterprise and open-source settings. We analyze two real-world deployments:(1) a multilingual privacy-preserving system integrated with Data and Model Factory, focusing on enterprise-scale data governance; and (2) PR Insights, an open-source repository emphasizing automated triaging and community-driven refinements. In Deployment 1, OneShield achieved a 0.95 F1 score in detecting sensitive entities like dates, names, and phone numbers across 26 languages, outperforming state-of-the-art tool such as StarPII and Presidio by up to 12\%. Deployment 2, with an average F1 score of 0.86, reduced manual effort by over 300 hours in three months, accurately flagging 8.25\% of 1,256 pull requests for privacy risks with enhanced context sensitivity. These results demonstrate OneShield's adaptability and efficacy in diverse environments, offering actionable insights for context-aware entity recognition, automated compliance, and ethical AI adoption. This work advances privacy-preserving frameworks, supporting user trust and compliance across operational contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12456 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications Asthana, Shubhi Zhang, Bing Mahindru, Ruchi DeLuca, Chad Gentile, Anna Lisa Gopisetty, Sandeep Cryptography and Security Artificial Intelligence Machine Learning Software Engineering The adoption of Large Language Models (LLMs) has revolutionized AI applications but poses significant challenges in safeguarding user privacy. Ensuring compliance with privacy regulations such as GDPR and CCPA while addressing nuanced privacy risks requires robust and scalable frameworks. This paper presents a detailed study of OneShield Privacy Guard, a framework designed to mitigate privacy risks in user inputs and LLM outputs across enterprise and open-source settings. We analyze two real-world deployments:(1) a multilingual privacy-preserving system integrated with Data and Model Factory, focusing on enterprise-scale data governance; and (2) PR Insights, an open-source repository emphasizing automated triaging and community-driven refinements. In Deployment 1, OneShield achieved a 0.95 F1 score in detecting sensitive entities like dates, names, and phone numbers across 26 languages, outperforming state-of-the-art tool such as StarPII and Presidio by up to 12\%. Deployment 2, with an average F1 score of 0.86, reduced manual effort by over 300 hours in three months, accurately flagging 8.25\% of 1,256 pull requests for privacy risks with enhanced context sensitivity. These results demonstrate OneShield's adaptability and efficacy in diverse environments, offering actionable insights for context-aware entity recognition, automated compliance, and ethical AI adoption. This work advances privacy-preserving frameworks, supporting user trust and compliance across operational contexts. |
| title | Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications |
| topic | Cryptography and Security Artificial Intelligence Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2501.12456 |