Collaborative Inference over Wireless Channels with Feature Differential Privacy
This work addresses privacy concerns for wireless edge devices in AI applications like sensing and computer vision, though it is incremental in combining existing privacy and communication techniques.
The paper tackles the privacy risks in collaborative inference over wireless channels by proposing a mechanism that secures feature transmission with differential privacy, achieving reduced communication overhead and formal privacy guarantees while maintaining classification accuracy with a lower bound.
Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage process: a) data acquisition through sensing, b) feature extraction, and c) feature encoding for transmission. However, transmitting the extracted features poses a significant privacy risk, as sensitive personal data can be exposed during the process. To address this challenge, we propose a novel privacy-preserving collaborative inference mechanism, wherein each edge device in the network secures the privacy of extracted features before transmitting them to a central server for inference. Our approach is designed to achieve two primary objectives: 1) reducing communication overhead and 2) ensuring strict privacy guarantees during feature transmission, while maintaining effective inference performance. Additionally, we introduce an over-the-air pooling scheme specifically designed for classification tasks, which provides formal guarantees on the privacy of transmitted features and establishes a lower bound on classification accuracy.