Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing latency and limiting exposure of raw input data. However, inference performance often degrades in practical deployments due to user-specific data distribution shifts, unreliable communication, and privacy-oriented perturbations, especially in closed environments where model architectures and parameters are inaccessible. To address this challenge, we propose SALT (Split-Adaptive Lightweight Tuning), a lightweight adaptation framework for closed Split Computing systems. SALT introduces a compact client-side adapter that refines intermediate representations produced by a frozen head network, enabling effective model adaptation without modifying the head or tail networks or increasing communication overhead. By modifying only the training conditions, SALT supports multiple adaptation objectives, including user personalization, communication robustness, and privacy-aware inference. Experiments using ResNet-18 on CIFAR-10 and CIFAR-100 show that SALT achieves higher accuracy than conventional retraining and fine-tuning while significantly reducing training cost. On CIFAR-10, SALT improves personalized accuracy from 88.1% to 93.8% while reducing training latency by more than 60%. SALT also maintains over 90% accuracy under 75% packet loss and preserves high accuracy (about 88% at sigma = 1.0) under noise injection. These results demonstrate that SALT provides an efficient and practical adaptation framework for real-world Split Computing systems.

翻译：拆分计算通过将深度神经网络划分为边缘端头部和服务器端尾部，实现边缘设备与云端的协同推理，从而降低延迟并限制原始输入数据的暴露。然而，在实际部署中，由于用户特定的数据分布偏移、不可靠的通信以及面向隐私的扰动，推理性能常常下降，尤其是在模型架构和参数不可访问的封闭环境中。为应对这一挑战，我们提出了SALT（拆分自适应轻量化调优），一种面向封闭式拆分计算系统的轻量化自适应框架。SALT引入了一个紧凑的客户端适配器，用于优化由冻结的头部网络产生的中间表示，从而在不修改头部或尾部网络、也不增加通信开销的情况下实现有效的模型自适应。通过仅修改训练条件，SALT支持多种自适应目标，包括用户个性化、通信鲁棒性和隐私感知推理。在CIFAR-10和CIFAR-100数据集上使用ResNet-18进行的实验表明，SALT相比传统的重新训练和微调方法获得了更高的准确率，同时显著降低了训练成本。在CIFAR-10上，SALT将个性化准确率从88.1%提升至93.8%，同时将训练延迟降低了60%以上。SALT在75%丢包率下仍能保持超过90%的准确率，并在噪声注入下（sigma = 1.0时约88%）保持高准确率。这些结果表明，SALT为现实世界的拆分计算系统提供了一个高效且实用的自适应框架。