Camouflage Learning: Feature Value Obscuring Ambient Intelligence for Constrained Devices

Abstract

Ambient intelligence demands collaboration schemes for distributed constrained devices which are not only highly energy efficient with respect to distributed sensing, processing and communication, but which also respect data privacy. Traditional algorithms for distributed processing suffer in Ambient intelligence domains either from limited data privacy, or from their excessive processing demands for constrained distributed devices. In this paper, we present Camouflage learning, a distributed machine learning scheme that obscures the trained model via probabilistic collaboration using physical-layer computation offloading and demonstrate the feasibility of the approach on backscatter communication prototypes and in comparison with federated learning, a popular distributed learning scheme. We show that Camouflage learning is more energy efficient than traditional schemes and that it requires less communication overhead while reducing the computation load through physical-layer computation offloading. The scheme is synchronization-agnostic and thus appropriate for sharply constrained, synchronization-incapable devices. We demonstrate model training and inference on four distinct datasets and investigate the performance of the scheme with respect to communication range, impact of challenging communication environments, power consumption, and the backscatter hardware prototype.

Secret Key Generation Between Ambient Backscatter Devices

“…While IoT has made it possible for things and people to interact with each other anytime and any place, the security of IoT devices has become a concern [1], [2]. Ambient Intelligence is based on collecting and using data from distributed sensing devices [3]. As the devices are communicating with each other or to some coordinator, it is important that the devices can trust to each other.…”

“…Instead of using a fixed infrastructure for key distribution, it would be more practical to generate the keys automatically when needed [5], [9]. In Camouflage Learning [3], data privacy is achieved using non-reversible aggregation of feature values, as no party has at time complete information on the underlying machine learning model.…”