大型语言模型的适应性个人身份信息缓解框架
Adaptive PII Mitigation Framework for Large Language Models
AI总结：
本文提出一个适应性PII缓解框架，利用NLP和策略驱动掩码动态对齐法规，在护照号码识别上F1达0.95，优于现有工具，并获用户高信任评分，为企业隐私合规提供可扩展方案。
摘要：
人工智能（AI）在全球范围内面临着不断演变的数据保护法律和执法实践带来的日益严峻的挑战。诸如GDPR和CCPA等法规对机器学习（ML）模型提出了严格的合规要求，尤其是在个人数据使用方面。这些法律赋予个人数据更正和删除等权利，使得依赖广泛数据集的大型语言模型（LLMs）的训练和部署变得复杂。公开数据的可用性并不能保证其在机器学习中的合法使用，这加剧了这些挑战。本文介绍了一个用于缓解大型语言模型中个人身份信息（PII）和敏感个人信息（SPI）风险的适应性系统。该系统动态地适应多样化的监管框架，并无缝集成到治理、风险和合规（GRC）系统中。该系统采用先进的自然语言处理技术、上下文感知分析和策略驱动的掩码机制，以确保法规合规性。基准测试凸显了该系统的有效性，其护照号码的F1分数为0.95，优于Microsoft Presidio（0.33）和Amazon Comprehend（0.54）等工具。在人工评估中，该系统获得了平均用户信任评分4.6/5，参与者认可其准确性和透明度。观察结果表明，与允许假名化和用户选择退出的CCPA相比，GDPR下的匿名化更为严格。这些结果验证了该系统作为企业隐私合规的可扩展且稳健的解决方案。
英文摘要：
Artificial Intelligence (AI) faces growing challenges from evolving data protection laws and enforcement practices worldwide. Regulations like GDPR and CCPA impose strict compliance requirements on Machine Learning (ML) models, especially concerning personal data use. These laws grant individuals rights such as data correction and deletion, complicating the training and deployment of Large Language Models (LLMs) that rely on extensive datasets. Public data availability does not guarantee its lawful use for ML, amplifying these challenges. This paper introduces an adaptive system for mitigating risk of Personally Identifiable Information (PII) and Sensitive Personal Information (SPI) in LLMs. It dynamically aligns with diverse regulatory frameworks and integrates seamlessly into Governance, Risk, and Compliance (GRC) systems. The system uses advanced NLP techniques, context-aware analysis, and policy-driven masking to ensure regulatory compliance. Benchmarks highlight the system's effectiveness, with an F1 score of 0.95 for Passport Numbers, outperforming tools like Microsoft Presidio (0.33) and Amazon Comprehend (0.54). In human evaluations, the system achieved an average user trust score of 4.6/5, with participants acknowledging its accuracy and transparency. Observations demonstrate stricter anonymization under GDPR compared to CCPA, which permits pseudonymization and user opt-outs. These results validate the system as a scalable and robust solution for enterprise privacy compliance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
