arXiv cs.CL· Mohamed Shaaban, Mohamed Elmahallawy, Thomas E. Carroll·· 12 小时前AI 评分39
Veil-then-Reveal：零信任用户–LLM 交互中的可逆伪匿名化 PII 保护框架
Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
AI 导读
Veil-then-Reveal（VtR）是一个用户侧 PII 伪匿名化框架，在零信任威胁模型下只向远程 LLM 提供商发送伪匿名化提示词，明文 PII 始终留在用户设备上。
正文 · 原文
Abstract:Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes data subjects and organizations to risks from logging, retention, model training, and unintended disclosure. Existing anonymization methods often mask or remove PII, while conventional encryption eliminates the lexical and structural cues needed for effective LLM processing. We present Veil-then-Reveal (VtR), a user-side PII pseudo-anonymization framework for privacy-preserving LLM interaction under a zero-trust threat model. VtR treats remote LLM providers as untrusted and sends only pseudo-anonymized prompts, keeping plaintext PII on the user. VtR first detects PII and replaces it with realistic, same-type, in-vocabulary surrogates before prompts leave the user's device, preserving their linguistic and structural properties. It combines format-preserving encryption (FPE) for structured PII, such as phone and credit-card numbers, with a keyed-hash dictionary and secure vault for semantic PII, such as names, locations, and organizations. Session-specific mappings provide cross-session unlinkability, while user-side restoration reversibly replaces surrogates with their original values in LLM responses. We further introduce a rank-class FPE strategy for dates that preserves format and ambiguity while reducing cipher evaluations. Evaluation on three datasets containing 11,322 annotated PII instances achieves 97.9% detection recall, 95.2% protection of detected values, and 99.9% round trip; 100% of echoed surrogates end-to-end round-trip restoration.
| Subjects: | Cryptography and Security (cs.CR); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22800 [cs.CR] |
| (or arXiv:2610.22800v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22800 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mohamed Elmahallawy [view email]
[v1]
Fri, 16 Oct 2026 01:24:42 UTC (212 KB)
来源：arXiv cs.CL · arxiv.org