OSNIP: 通过混淆语义空域打破LLM推理中的隐私-效用-效率三元困境
OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
AI总结：
OSNIP通过混淆语义空域技术，在LLM推理中实现隐私、效用和效率的平衡，有效降低攻击成功率并保持模型性能。
摘要：
我们提出Obfuscated Semantic Null space Injection for Privacy（OSNIP），一种轻量级的客户端加密框架，用于隐私保护的LLM推理。通过将线性内核的几何直觉推广到LLM的高维潜在空间，我们正式定义了“混淆语义空域”，这是一个高维区域，能够在保持语义保真度的同时，强制原始嵌入与近正交。通过注入将原始嵌入投影到该空间的扰动，OSNIP在无需任何后处理的情况下确保隐私。此外，OSNIP采用依赖密钥的随机映射，生成每个用户独有的扰动轨迹。在12个生成和分类基准上的评估表明，OSNIP实现了最先进的性能，显著降低了攻击成功率，同时在严格的安全约束下保持了强大的模型效用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
