SRPG: Semantically Reconstructed Privacy Guard for Zero-Trust Privacy in Educational Multi-Agent Systems

TL;DR

SRPG is a privacy-preserving mechanism for educational multi-agent systems that effectively prevents PII leakage while maintaining instructional quality, using a dual-stream reconstruction approach with LLMs.

Contribution

It introduces SRPG, a novel dual-stream reconstruction mechanism that balances privacy and utility in educational MAS with unstructured dialogue.

Findings

Achieves zero PII leakage with GPT-4o (ASR 0.0000)

Maintains high instructional accuracy (Exact Match 0.8267)

Outperforms baseline privacy methods

Abstract

Multi-Agent Systems (MAS) with large language models (LLMs) enable personalized education but risk leaking minors personally identifiable information (PII) via unstructured dialogue. Existing privacy methods struggle to balance security and utility: role-based access control fails on unstructured text, while naive masking destroys pedagogical context. We propose SRPG, a privacy guard for educational MAS, using a Dual-Stream Reconstruction Mechanism: a strict sanitization stream ensures zero PII leakage, and a context reconstruction stream (LLM driven) recovers mathematical logic. This decouples instructional content from private data, preserving teaching efficacy. Tests on MathDial show SRPG works across models; with GPT-4o, it achieves 0.0000 Attack Success Rate (ASR) (zero leakage) and 0.8267 Exact Match, far outperforming the zero trust Pure LLM baseline (0.2138). SRPG effectively protects minors privacy without sacrificing mathematical instructional quality.