OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space

📅 2026-01-30
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the trilemma in large language model (LLM) inference—balancing privacy preservation, model utility, and computational efficiency—by proposing a lightweight client-side encryption framework. It introduces, for the first time, a formal definition of the “obfuscated semantic nullspace,” into which input embeddings are projected to achieve privacy without requiring post-processing. The method integrates user-key-driven random perturbation trajectories with geometry-aware noise injection in the latent space, enabling personalized privacy guarantees while maintaining efficient inference. Evaluated across twelve generative and classification benchmarks, the approach achieves state-of-the-art performance, substantially reducing attack success rates while preserving high model utility under stringent security constraints.

Technology Category

Application Category

📝 Abstract
We propose Obfuscated Semantic Null space Injection for Privacy (OSNIP), a lightweight client-side encryption framework for privacy-preserving LLM inference. Generalizing the geometric intuition of linear kernels to the high-dimensional latent space of LLMs, we formally define the ``Obfuscated Semantic Null Space'', a high-dimensional regime that preserves semantic fidelity while enforcing near-orthogonality to the original embedding. By injecting perturbations that project the original embedding into this space, OSNIP ensures privacy without any post-processing. Furthermore, OSNIP employs a key-dependent stochastic mapping that synthesizes individualized perturbation trajectories unique to each user. Evaluations on 12 generative and classification benchmarks show that OSNIP achieves state-of-the-art performance, sharply reducing attack success rates while maintaining strong model utility under strict security constraints.
Problem

Research questions and friction points this paper is trying to address.

privacy
utility
efficiency
LLM inference
trilemma
Innovation

Methods, ideas, or system contributions that make the work stand out.

Obfuscated Semantic Null Space
privacy-preserving LLM inference
client-side encryption
semantic fidelity
stochastic perturbation
Z
Zhiyuan Cao
Shanghai Key Laboratory of Computer Software Testing and Evaluating
Z
Zeyu Ma
Shanghai Normal University
C
Chenhao Yang
Shanghai Polytechnic University
H
Han Zheng
TrustAI Pte. Ltd.
M
Mingang Chen
Shanghai Key Laboratory of Computer Software Testing and Evaluating