Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Asthana, Shubhi, Zhang, Bing, Mahindru, Ruchi, DeLuca, Chad, Gentile, Anna Lisa, Gopisetty, Sandeep
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