SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs
Year: 2026
Type: conference-paper
Abstract: 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 dualadapter 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 31.66×reduction in inference attack accuracy and a 17.07× reduction in extraction recall for unauthorized requests.
Authors: Mohamed Shaaban, Mohamed Elmahallawy
Institution: Washington State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166871266