SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs

Mohamed Shaaban, Mohamed Elmahallawy


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 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. Code is available at https://github.com/wsu-cyber-security-lab-ai/SecureGate.
Anthology ID:
2026.acl-long.1972
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
42593–42610
Language:
URL:
https://aclanthology.org/2026.acl-long.1972/
DOI:
10.18653/v1/2026.acl-long.1972
Bibkey:
Cite (ACL):
Mohamed Shaaban and Mohamed Elmahallawy. 2026. SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 42593–42610, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs (Shaaban & Elmahallawy, ACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.acl-long.1972.pdf
Checklist:
 2026.acl-long.1972.checklist.pdf