Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference
This addresses privacy concerns for IoT systems using remote inference, but it is incremental as it builds on existing obfuscation techniques.
The paper tackles the privacy risk of transmitting raw inference data from IoT edge devices to a remote backend by proposing a lightweight obfuscation method that uses a small neural network at the edge, effectively protecting data confidentiality while preserving backend inference accuracy as shown in three case studies.
Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inference scheme incurs concerns regarding the privacy of the inference data transmitted by the edge devices to the curious backend. This paper presents a lightweight and unobtrusive approach to obfuscate the inference data at the edge devices. It is lightweight in that the edge device only needs to execute a small-scale neural network; it is unobtrusive in that the edge device does not need to indicate whether obfuscation is applied. Extensive evaluation by three case studies of free spoken digit recognition, handwritten digit recognition, and American sign language recognition shows that our approach effectively protects the confidentiality of the raw forms of the inference data while effectively preserving the backend's inference accuracy.