HEEDFUL: Leveraging Sequential Transfer Learning for Robust WiFi Device Fingerprinting Amid Hardware Warm-Up Effects

• URL: http://arxiv.org/abs/2602.00338v1
• Date: Fri, 30 Jan 2026 21:41:19 GMT
• Title: HEEDFUL: Leveraging Sequential Transfer Learning for Robust WiFi Device Fingerprinting Amid Hardware Warm-Up Effects
• Authors: Abdurrahman Elmaghbub, Bechir Hamdaoui,
• Abstract summary: HEEDFUL is a novel framework harnessing sequential transfer learning and targeted impairment estimation.<n>Our evaluation showcases HEEDFUL's efficacy, achieving remarkable classification accuracies of up to 96% during the initial device operation intervals.<n>We release WiFi type B and N RF fingerprint datasets that, for the first time, incorporate both the time-domain representation and real hardware impairments.
• Score: 3.8673630752805437
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep Learning-based RF fingerprinting approaches struggle to perform well in cross-domain scenarios, particularly during hardware warm-up. This often-overlooked vulnerability has been jeopardizing their reliability and their adoption in practical settings. To address this critical gap, in this work, we first dive deep into the anatomy of RF fingerprints, revealing insights into the temporal fingerprinting variations during and post hardware stabilization. Introducing HEEDFUL, a novel framework harnessing sequential transfer learning and targeted impairment estimation, we then address these challenges with remarkable consistency, eliminating blind spots even during challenging warm-up phases. Our evaluation showcases HEEDFUL's efficacy, achieving remarkable classification accuracies of up to 96% during the initial device operation intervals-far surpassing traditional models. Furthermore, cross-day and cross-protocol assessments confirm HEEDFUL's superiority, achieving and maintaining high accuracy during both the stable and initial warm-up phases when tested on WiFi signals. Additionally, we release WiFi type B and N RF fingerprint datasets that, for the first time, incorporate both the time-domain representation and real hardware impairments of the frames. This underscores the importance of leveraging hardware impairment data, enabling a deeper understanding of fingerprints and facilitating the development of more robust RF fingerprinting solutions.

Related papers

• Antidistillation Fingerprinting [119.66677613290359]
  We introduce antidistillation fingerprinting (ADFP), a principled approach that aligns the fingerprinting objective with the student's learning dynamics.<n>ADFP achieves a significant improvement over state-of-the-art baselines, stronger detection confidence with minimal impact on utility, even when the student model's architecture is unknown.
  arXiv  Detail & Related papers  (2026-02-03T18:15:50Z)
• WiFi-based Cross-Domain Gesture Recognition Using Attention Mechanism [61.79272554643873]
  We propose a gesture recognition network that integrates a multi-semantic attention mechanism with a self-attention-based channel mechanism.<n>The results show that it not only maintains high in-domain accuracy of 99.72%, but also achieves high performance in cross-domain recognition of 97.61%.
  arXiv  Detail & Related papers  (2025-12-04T07:09:13Z)
• Bluetooth Fingerprint Identification Under Domain Shift Through Transient Phase Derivative [5.3898004059026325]
  Deep learning-based radio frequency fingerprinting (RFFP) has become an enabling physical-layer security technology.<n>For Bluetooth Low Energy (BLE) devices, addressing these challenges is particularly crucial due to the BLE protocol's frequency-hopping nature.<n>In this work, and for the first time, we investigated the frequency hopping effect on RFFP of BLE devices, and proposed a novel, low-cost, domain-adaptive feature extraction method.
  arXiv  Detail & Related papers  (2025-10-11T00:39:38Z)
• Enhancing Test Time Adaptation with Few-shot Guidance [62.49199492255226]
  Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data.<n>Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data.<n>We develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA.
  arXiv  Detail & Related papers  (2024-09-02T15:50:48Z)
• Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts [4.002351785644765]
  This work introduces "accumulation score" as a novel approach to capturing fine-grained channel dynamics. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification.
  arXiv  Detail & Related papers  (2024-05-15T22:34:52Z)
• Towards Adaptive RF Fingerprint-based Authentication of IIoT devices [0.0]
  We present a first step towards achieving powerful and flexible IIoT device authentication, by leveraging AI adaptive Radio Frequency Fingerprinting technique selection and tuning, at the PHY layer for highly accurate device authentication over challenging RF environments.
  arXiv  Detail & Related papers  (2023-11-27T14:55:32Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• On the Impact of the Hardware Warm-Up Time on Deep Learning-Based RF Fingerprinting [7.8344795632171325]
  We investigate the impact of device hardware stabilization and warm-up time on the achievable fingerprinting performances.<n>Our results show that when the deep learning models are trained with data samples captured after the hardware stabilizes but tested with data captured right after powering on the devices, the device classification accuracy drops below 37%.<n>When both the training and testing data are captured after the stabilization period, the achievable average accuracy exceeds 99%.
  arXiv  Detail & Related papers  (2023-07-31T21:11:27Z)
• Agile gesture recognition for capacitive sensing devices: adapting on-the-job [55.40855017016652]
  We demonstrate a hand gesture recognition system that uses signals from capacitive sensors embedded into the etee hand controller. The controller generates real-time signals from each of the wearer five fingers. We use a machine learning technique to analyse the time series signals and identify three features that can represent 5 fingers within 500 ms.
  arXiv  Detail & Related papers  (2023-05-12T17:24:02Z)
• AFR-Net: Attention-Driven Fingerprint Recognition Network [47.87570819350573]
  We improve initial studies on the use of vision transformers (ViT) for biometric recognition, including fingerprint recognition. We propose a realignment strategy using local embeddings extracted from intermediate feature maps within the networks to refine the global embeddings in low certainty situations. This strategy can be applied as a wrapper to any existing deep learning network (including attention-based, CNN-based, or both) to boost its performance.
  arXiv  Detail & Related papers  (2022-11-25T05:10:39Z)
• Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes [10.698553177585973]
  We study and analyze the sensitivity of LoRa RF fingerprinting to various network setting changes. We propose a new fingerprinting technique that exploits out-of-band distortion information to increase the fingerprinting accuracy. Our results show that fingerprinting does relatively well when the learning models are trained and tested under the same settings.
  arXiv  Detail & Related papers  (2022-08-31T16:53:05Z)
• GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi [52.530330427538885]
  WiFi-based human action recognition (HAR) has been regarded as a promising solution in applications such as smart living and remote monitoring. We propose an end-to-end Gabor residual anti-aliasing sensing network (GraSens) to directly recognize the actions using the WiFi signals from the wireless devices in diverse scenarios.
  arXiv  Detail & Related papers  (2022-05-24T10:20:16Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• Real-time single image depth perception in the wild with handheld devices [45.26484111468387]
  Two main issues limit depth estimation from handheld devices in-the-wild. We show how they are both addressable adopting appropriate network design and training strategies. We report experimental results concerning real-time depth-aware augmented reality and image blurring with smartphones in-the-wild.
  arXiv  Detail & Related papers  (2020-06-10T08:30:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.