GAMA: A General Anonymizing Multi-Agent System for Privacy Preservation Enhanced by Domain Rules and Disproof Method

2025-09-12

AI Summary

To address privacy risks arising from hosting large language models (LLMs) for multi-agent systems (MAS) on public remote servers, this paper proposes GAMA—a General Anonymous MAS framework. GAMA strictly separates private and public spaces to ensure sensitive data is processed locally, preventing leakage of raw private information. It introduces two novel mechanisms: Domain Rule Knowledge Enhancement (DRKE) and Disproof-based Logical Enhancement (DLE), which jointly mitigate semantic degradation under anonymization constraints. Extensive experiments across four NLP benchmarks demonstrate that GAMA outperforms existing methods in question-answering tasks while achieving state-of-the-art performance in both knowledge masking and logical privacy preservation. Notably, this work pioneers the integration of structured anonymization with collaborative multi-agent reasoning, establishing a verifiable and scalable paradigm for deploying privacy-sensitive LLM-based agents.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Learning
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

With the rapid advancement of Large Language Model (LLM), LLM-based agents exhibit exceptional abilities in understanding and generating natural language, facilitating human-like collaboration and information transmission in LLM-based Multi-Agent System (MAS). High-performance LLMs are often hosted on remote servers in public spaces. When tasks involve privacy data, MAS cannot securely utilize these LLMs without implementing privacy-preserving mechanisms. To address this challenge, we propose a General Anonymizing Multi-Agent system (GAMA), which divides the agents' workspace into private and public spaces and protects privacy through the anonymizing mechanism. In the private space, agents handle sensitive data, while in the public space, only anonymized data is utilized. GAMA incorporates two key modules to mitigate semantic loss caused by anonymization: Domain-Rule-based Knowledge Enhancement (DRKE) and Disproof-based Logic Enhancement (DLE). We evaluate GAMA on two public question-answering datasets: Trivia Creative Writing and Logic Grid Puzzle. The results demonstrate that GAMA has superior performance compared to the state-of-the-art models. To further assess its privacy-preserving capabilities, we designed two new datasets: Knowledge Privacy Preservation and Logic Privacy Preservation. The final results highlight GAMA's exceptional effectiveness in both task processing and privacy preservation.

Problem

• Protecting privacy in multi-agent systems using LLMs
• Anonymizing sensitive data between private and public spaces
• Reducing semantic loss from anonymization with enhancement modules

Innovation

• Divides workspace into private and public spaces
• Uses Domain-Rule-based Knowledge Enhancement module
• Implements Disproof-based Logic Enhancement module