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.
@article{arxiv.2601.22752,
title = {OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space},
author = {Zhiyuan Cao and Zeyu Ma and Chenhao Yang and Han Zheng and Mingang Chen},
journal= {arXiv preprint arXiv:2601.22752},
year = {2026}
}