2025/12/03 by Shuang Guo, Guo, Shuang, Zihui Li +1
Computer Science · #Access control #Advanced Graph Neural Networks #Confidentiality #Context (archaeology) #FOS: Computer and information sciences #Guard (computer science) #Information privacy #Intelligent Tutoring Systems and Adaptive Learning #Masking (illustration) #Multiagent Systems (cs.MA) #Privacy software #Privacy-Preserving Technologies in Data #Private information retrieval
paper · pdf · doi:10.48550/arxiv.2512.03694
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/12/03 · openalex created_date 2025/12/05 · openalex updated_date 2026/07/28
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.