paper-with-me

Papers

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

2025-01-21 · Shubhi Asthana, Bing Zhang, Ruchi Mahindru, Chad Deluca, Anna Lisa Gentile, Sandeep Gopisetty

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.

📄 PDF Abstract BibTeX arXiv:2501.12456

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

Current state of LLM Risks and AI Guardrails

2024-06-16 · Suriya Ganesh Ayyamperumal, Limin Ge

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying t…

FairnessRAGRetrieval-augmented Generation

FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework

2025-02-27 · S M Sarwar

With the increasing prevalence of mental health conditions worldwide, AI-powered chatbots and conversational agents have emerged as accessible tools to support mental health. However, deploying Large Language Models (LLM…

Computational EfficiencyFederated LearningPrivacy Preserving

Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical Reasoning

2025-02-13 · Leon Nissen, Philipp Zagar, Vishnu Ravi, Aydin Zahedivash 외

The deployment of Large Language Models (LLM) on mobile devices offers significant potential for medical applications, enhancing privacy, security, and cost-efficiency by eliminating reliance on cloud-based services and …

Computational Efficiency

Challenges in Guardrailing Large Language Models for Science

2024-11-12 · Nishan Pantha, Muthukumaran Ramasubramanian, Iksha Gurung, Manil Maskey 외

The rapid development in large language models (LLMs) has transformed the landscape of natural language processing and understanding (NLP/NLU), offering significant benefits across various domains. However, when applied …

Ethics

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks

2024-09-26 · Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Muhammad Zaid Hameed 외

The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLM…

Computational Efficiency