AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI systems rely both on efficient model learning and inference. In the inference phase, features extracted from sensing data are utilized for prediction tasks (e.g., classification or regression). In edge networks, sensors and model servers are often not co-located, which requires communication of features. As sensitive personal data can be reconstructed by an adversary, transformation of the features are required to reduce the risk of privacy violations. While differential privacy mechanisms provide a means of protecting finite datasets, protection of individual features has not been addressed. In this paper, we propose a novel framework for privacy-preserving AI-based sensing, where devices apply transformations of extracted features before transmission to a model server.

翻译：基于人工智能的无线边缘设备感知技术具有显著增强人工智能应用的潜力，尤其在自动驾驶和环境监测等视觉与感知任务中。人工智能系统既依赖于高效的模型学习，也依赖于推理过程。在推理阶段，从感知数据中提取的特征被用于预测任务（如分类或回归）。在边缘网络中，传感器与模型服务器通常不位于同一位置，这需要特征数据的通信传输。由于敏感个人数据可能被攻击者重构，必须对特征进行变换以降低隐私泄露风险。尽管差分隐私机制为保护有限数据集提供了方法，但个体特征的保护尚未得到充分研究。本文提出了一种新颖的隐私保护人工智能感知框架，其中设备在将提取的特征传输至模型服务器之前对其进行变换处理。