Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing

View PDF HTML (experimental)

Abstract:The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the "Inseparability Paradigm": advanced context management intrinsically coincides with privacy management. We propose a local "Privacy Guard" -- a holistic contextual observer powered by an on-premise Small Language Model (SLM) -- that performs abstractive summarisation and Automatic Prompt Optimisation (APO) to decompose prompts into focused sub-tasks, re-routing high-risk queries to Zero-Trust or NDA-covered models. This dual mechanism simultaneously eliminates sensitive inference vectors (Zero Leakage) and reduces cloud token payloads (OpEx Reduction). A LIFO-based context compacting mechanism further bounds working memory, limiting the emergent leakage surface. We validate the framework through a 2x2 benchmark (Lazy vs. Expert users; Personal vs. Institutional secrets) on a 1,000-sample dataset, achieving a 45% blended OpEx reduction, 100% redaction success on personal secrets, and -- via LLM-as-a-Judge evaluation -- an 85% preference rate for APO-compressed responses over raw baselines. Our results demonstrate that Token Parsimony and Zero Leakage are mathematically dual projections of the same contextual compression operator.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)

Cite as: arXiv:2603.28972 [cs.CR]

(or arXiv:2603.28972v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2603.28972

arXiv-issued DOI via DataCite

Submission history

From: Alessio Langiu [view email] [v1] Mon, 30 Mar 2026 20:16:42 UTC (1,689 KB)