# Uncovering the Portability Limitation of Deep Learning-Based Wireless Device Fingerprints

arXiv: https://arxiv.org/abs/2211.07687 · HTML: https://mlsanity.com/paper/2211.07687/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks](https://mlsanity.com/paper/1812.01124/) (2018)
- [Deep Neural Network Feature Designs for RF Data-Driven Wireless Device Classification](https://mlsanity.com/paper/2105.02755/) (2021)
- [Comprehensive RF Dataset Collection and Release: A Deep Learning-Based Device Fingerprinting Use Case](https://mlsanity.com/paper/2201.02213/) (2022)
- [Can You Fix My Neural Network? Real-Time Adaptive Waveform Synthesis for Resilient Wireless Signal Classification](https://mlsanity.com/paper/2103.03745/) (2021)
- [Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes](https://mlsanity.com/paper/2208.14964/) (2022)
- [Tweak: Towards Portable Deep Learning Models for Domain-Agnostic LoRa Device Authentication](https://mlsanity.com/paper/2209.00786/) (2022)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift](https://mlsanity.com/paper/2403.04036/) (2024)

## Abstract (arXiv)

Recent device fingerprinting approaches rely on deep learning to extract device-specific features solely from raw RF signals to identify, classify and authenticate wireless devices. One widely known issue lies in the inability of these approaches to maintain good performances when the training data and testing data are collected under varying deployment domains. For example, when the learning model is trained on data collected from one receiver but tested on data collected from a different receiver, the performance degrades substantially compared to when both training and testing data are collected using the same receiver. The same also happens when considering other varying domains, like channel condition and protocol configuration. In this paper, we begin by explaining, through testbed experiments, the challenges these fingerprinting techniques face when it comes to domain portability. We will then present some ideas on how to go about addressing these challenges so as to make deep learning-based device fingerprinting more resilient to domain variability.