提出混合模型与隐私保护机制，提升无卫星环境下的导航精度与数据安全。
ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation
- 融合ConvNeXt与Transformer的分层结构，增强惯性导航特征提取能力。
- 在多个基准数据集上定位精度提升超40%，同时满足(ε,δ)-差分隐私要求。
- 适用于工业场景中强干扰环境，适合对安全与智能导航有高要求的系统。
基于数据的惯性序列学习已革新无卫星环境下的导航技术，相比传统贝叶斯方法提供更优的里程计分辨率。然而，深度学习惯性追踪系统仍易遭隐私泄露，可能暴露敏感训练数据。现有差分隐私方案常因引入过多噪声而损害模型性能，尤其在高频惯性测量中更为明显。本文提出ConvXformer，一种融合ConvNeXt块与Transformer编码器的分层混合架构，用于鲁棒惯性导航。设计了一种高效的差分隐私机制，结合自适应梯度裁剪与梯度对齐噪声注入（GANI），在保护敏感信息的同时保障模型性能。框架采用截断奇异值分解进行梯度处理，实现对隐私-效用权衡的精确控制。在基准数据集OxIOD、RIDID、RoNIN上的全面评估表明，ConvXformer超越现有最先进方法，在定位精度上提升超过40%，并满足(ε,δ)-差分隐私保证。为验证真实世界表现，我们构建了机械工程楼内采集的Mech-IO数据集，其中工业设备产生的强磁场引发显著传感器扰动。实验显示该框架在严重环境畸变下仍具鲁棒性，适用于网络安全与智能导航融合的网络物理系统。
原文摘要 · Abstract (English)
Data-driven inertial sequence learning has revolutionized navigation in GPS-denied environments, offering superior odometric resolution compared to traditional Bayesian methods. However, deep learning-based inertial tracking systems remain vulnerable to privacy breaches that can expose sensitive training data. \hl{Existing differential privacy solutions often compromise model performance by introducing excessive noise, particularly in high-frequency inertial measurements.} In this article, we propose ConvXformer, a hybrid architecture that fuses ConvNeXt blocks with Transformer encoders in a hierarchical structure for robust inertial navigation. We propose an efficient differential privacy mechanism incorporating adaptive gradient clipping and gradient-aligned noise injection (GANI) to protect sensitive information while ensuring model performance. Our framework leverages truncated singular value decomposition for gradient processing, enabling precise control over the privacy-utility trade-off. Comprehensive performance evaluations on benchmark datasets (OxIOD, RIDI, RoNIN) demonstrate that ConvXformer surpasses state-of-the-art methods, achieving more than 40% improvement in positioning accuracy while ensuring $(ε,δ)$-differential privacy guarantees. To validate real-world performance, we introduce the Mech-IO dataset, collected from the mechanical engineering building at KAIST, where intense magnetic fields from industrial equipment induce significant sensor perturbations. This demonstrated robustness under severe environmental distortions makes our framework well-suited for secure and intelligent navigation in cyber-physical systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。