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

arXiv: https://arxiv.org/abs/2602.13529 · HTML: https://mlsanity.com/paper/2602.13529/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks](https://mlsanity.com/paper/2104.08815/) (2021)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities](https://mlsanity.com/paper/2408.13296/) (2024)
- [FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning](https://mlsanity.com/paper/2406.07925/) (2024)
- [Dual-Personalizing Adapter for Federated Foundation Models](https://mlsanity.com/paper/2403.19211/) (2024)
- [Recent Advances on Federated Learning: A Systematic Survey](https://mlsanity.com/paper/2301.01299/) (2023)
- [pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning](https://mlsanity.com/paper/2310.13283/) (2023)
- [Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors](https://mlsanity.com/paper/2411.01705/) (2024)
- [Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data](https://mlsanity.com/paper/2409.11423/) (2024)
- [Differential Privacy Techniques for Cyber Physical Systems: A Survey](https://mlsanity.com/paper/1812.02282/) (2018)
- [Towards Trustworthy Federated Learning with Untrusted Participants](https://mlsanity.com/paper/2505.01874/) (2025)

## Abstract (arXiv)

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.