为大模型设计动态隐私控制框架，确保敏感信息仅对可信用户开放。
Trustworthy AI: Securing Sensitive Data in Large Language Models
- 基于用户信任度动态控制敏感信息输出
- 融合实体识别与上下文分析识别敏感内容
- 适合医疗金融等高风险场景的模型部署
大型语言模型（LLMs）在自然语言处理中实现了强大的文本生成与理解能力，但其在医疗、金融、法律等敏感领域的应用引发了隐私与数据安全的担忧。本文提出一种综合框架，通过嵌入信任机制实现对敏感信息的动态披露控制。该框架包含三个核心组件：用户信任画像、信息敏感度检测与自适应输出控制。利用基于角色的访问控制（RBAC）、基于属性的访问控制（ABAC）、命名实体识别（NER）、上下文分析及差分隐私等技术，系统根据用户信任等级决定是否披露敏感信息。该方案在保障数据可用性的同时强化隐私保护，为高风险场景下的大模型安全部署提供新思路。未来工作将拓展至多领域测试，评估其在保持系统效率前提下的实际效果。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises critical concerns about privacy and data security. This paper proposes a comprehensive framework for embedding trust mechanisms into LLMs to dynamically control the disclosure of sensitive information. The framework integrates three core components: User Trust Profiling, Information Sensitivity Detection, and Adaptive Output Control. By leveraging techniques such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), Named Entity Recognition (NER), contextual analysis, and privacy-preserving methods like differential privacy, the system ensures that sensitive information is disclosed appropriately based on the user's trust level. By focusing on balancing data utility and privacy, the proposed solution offers a novel approach to securely deploying LLMs in high-risk environments. Future work will focus on testing this framework across various domains to evaluate its effectiveness in managing sensitive data while maintaining system efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。