SecureGate: 通过令牌门控双适配器安全学习何时揭示PII
SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs
AI总结：
SecureGate通过令牌门控双适配器框架，在联邦LLM微调中实现细粒度隐私控制，减少PII泄露并提升任务效用。
摘要：
联邦学习（FL）能够在不共享原始数据的情况下跨组织孤岛进行协作训练，使其在隐私敏感应用中具有吸引力。随着大语言模型（LLM）的快速采用，联邦微调生成式LLM已成为利用分布式数据并保持保密性的一种方法。然而，这种设置引入了根本性挑战：（i）由于LLM记忆导致的个人身份信息（PII）泄露，以及（ii）在异构数据下的全局泛化与本地效用之间的持续矛盾。现有防御措施，如数据清洗和差分隐私，虽然减少了泄露，但通常会降级下游性能。我们提出SecureGate，一种用于LLM的隐私感知联邦微调框架，提供细粒度隐私控制而不牺牲效用。SecureGate采用双适配器LoRA架构：一个安全适配器学习经过清洗的全局共享表示，另一个揭示适配器捕捉敏感的组织特定知识。一个令牌控制的门控模块在推理时选择性地激活这些适配器，从而在不重新训练的情况下实现受控的信息披露。在多个LLM和真实世界数据集上的广泛实验表明，SecureGate在提高任务效用的同时显著减少了PII泄露，实现了高达31.66倍的推理攻击准确率降低和17.07倍的未经授权请求提取召回率降低。此外，它保持了100%的正确适配器路由可靠性，并仅带来极小的计算和通信开销。
英文摘要：
Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs), federated fine-tuning of generative LLMs has gained attention as a way to leverage distributed data while preserving confidentiality. However, this setting introduces fundamental challenges: (i) privacy leakage of personally identifiable information (PII) due to LLM memorization, and (ii) a persistent tension between global generalization and local utility under heterogeneous data. Existing defenses, such as data sanitization and differential privacy, reduce leakage but often degrade downstream performance. We propose SecureGate, a privacy-aware federated fine-tuning framework for LLMs that provides fine-grained privacy control without sacrificing utility. SecureGate employs a dual-adapter LoRA architecture: a secure adapter that learns sanitized, globally shareable representations, and a revealing adapter that captures sensitive, organization-specific knowledge. A token-controlled gating module selectively activates these adapters at inference time, enabling controlled information disclosure without retraining. Extensive experiments across multiple LLMs and real-world datasets show that SecureGate improves task utility while substantially reducing PII leakage, achieving up to a 31.66X reduction in inference attack accuracy and a 17.07X reduction in extraction recall for unauthorized requests. Additionally, it maintains 100% routing reliability to the correct adapter and incurs only minimal computational and communication overhead.
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。
