Approaches to Secure Inference in the Internet of Things: Performance Bounds, Algorithms, and Effective Attacks on IoT Sensor Networks

摘要

The Internet of Things (IoT) improves pervasive sensing and control capabilities via the aid of modern digital communication, signal processing, and massive deployment of sensors but presents severe security challenges. Attackers can modify the data entering or communicated from the IoT sensors, which can have a serious impact on any algorithm using these data for inference. This article describes how to provide tight bounds (with sufficient data) on the performance of the best unbiased algorithms estimating a parameter from the attacked data and communications under any assumed statistical model describing how the sensor data depends on the parameter before attack. The results hold regardless of the unbiased estimation algorithm adopted, which could employ deep learning, machine learning, statistical signal processing, or any other approach. Example algorithms that achieve performance close to these bounds are illustrated. Attacks that make the attacked data useless for reducing these bounds are also described. These attacks provide a guaranteed attack performance in terms of the bounds regardless of the algorithms the unbiased estimation system employs. References are supplied that provide various extensions to all of the specific results presented in this article and a brief discussion of low-complexity encryption and physical layer security is provided.