Waveform-Defined Privacy: A Signal Solution to Protect Wireless Sensing
Wireless signals are commonly used for communications. Emerging applications are giving new functions to wireless signals, in which wireless sensing is the most attractive one. Channel state information (CSI) is not only the parameter for channel equalization in communications but also the indicator for wireless sensing. However, due to the broadcast nature of wireless signals, eavesdroppers can easily capture legitimate user signals and violate user privacy by measuring CSI. Moreover, the advancement of hardware simplifies illegal eavesdropping since smart devices can track over-the-air signals through walls. Therefore, this work considers a waveform-defined privacy (WDP) solution that can hide CSI phase information and therefore protect user privacy. Besides, the proposed waveform solution achieves better performance due to the use of a unique modulation mechanism. Additionally, by tuning a waveform parameter, the waveform can also enhance communication security.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
In this paper, we consider privacy aspects of wireless federated learning (FL) with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. By exploiting the waveform superpositi…
Federated LearningSynthesis of Realistic ECG using Generative Adversarial Networks
Access to medical data is highly restricted due to its sensitive nature, preventing communities from using this data for research or clinical training. Common methods of de-identification implemented to enable the sharin…
De-identificationInference AttackMembership Inference AttackTime Series+1Dynamic Privacy Allocation for Locally Differentially Private Federated Learning with Composite Objectives
This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The p…
Federated LearningEfficient Machine Learning Approach for Optimizing the Timing Resolution of a High Purity Germanium Detector
We describe here an efficient machine-learning based approach for the optimization of parameters used for extracting the arrival time of waveforms, in particular those generated by the detection of 511 keV annihilation g…
BIG-bench Machine LearningvalidA compressive multi-kernel method for privacy-preserving machine learning
As the analytic tools become more powerful, and more data are generated on a daily basis, the issue of data privacy arises. This leads to the study of the design of privacy-preserving machine learning algorithms. Given t…
Activity RecognitionBIG-bench Machine LearningPerson IdentificationPrivacy Preserving