# Characterizing and Mitigating the Effects of Device Temperature on RF Fingerprinting Accuracy

arXiv: https://arxiv.org/abs/2607.25070 · HTML: https://mlsanity.com/paper/2607.25070/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions](https://mlsanity.com/paper/1909.00590/) (2019)
- [Transformers in Time-series Analysis: A Tutorial](https://mlsanity.com/paper/2205.01138/) (2022)
- [Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa](https://mlsanity.com/paper/2107.02867/) (2021)
- [EPS: Distinguishable IQ Data Representation for Domain-Adaptation Learning of Device Fingerprints](https://mlsanity.com/paper/2308.04467/) (2023)
- [Domain-Adaptive Device Fingerprints for Network Access Authentication Through Multifractal Dimension Representation](https://mlsanity.com/paper/2308.07925/) (2023)
- [Bluetooth Fingerprint Identification Under Domain Shift Through Transient Phase Derivative](https://mlsanity.com/paper/2510.09940/) (2025)
- [Replicating the Signature: Unsupervised Targeted Impersonation Attack on RF Fingerprinting](https://mlsanity.com/paper/2607.05549/) (2026)

## Abstract (arXiv)

Radio Frequency Fingerprinting (RFFP) has emerged as a promising approach for device authentication by exploiting hardware-specific impairments embedded in transmitted signals. Yet existing methods largely overlook a major drawback: RFFP sensitivity to temperature--a critical factor influenced by both internal and environmental conditions--which can significantly alter device signatures and degrade classification performance. In this paper, we propose a novel temperature-aware RFFP framework that explicitly incorporates device temperature information into the learning process to improve robustness and generalization. We evaluate the proposed method on a real-world Bluetooth Low Energy (BLE) dataset collected across multiple devices and environmental conditions. Experimental results demonstrate that temperature-aware modeling consistently outperforms other temperature mitigation baselines, achieving significant improvements in classification accuracy, particularly under unseen temperature and environmental conditions.