Open Set Wireless Transmitter Authorization: Deep Learning Approaches and Dataset Considerations

Hanna, Samer; Karunaratne, Samurdhi; Čabrić, Danijela

doi:10.1109/tccn.2020.3043332

Cited by 66 publications

(26 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having many transmitters can enable using more practical formulations of the problem. For instance, instead of classifying among a closed set of known transmitters, open set recognition enables rejecting unauthorized transmitters unseen in training [12]. The challenge in developing these systems is that different Tx are needed for training and testing, as unauthorized transmitters cannot be exposed during training.…”

Section: Impact Of Number Of Transmittersmentioning

confidence: 99%

See 1 more Smart Citation

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

2022

Self Cite

View full text Add to dashboard Cite

RF fingerprinting leverages circuit-level variability of transmitters to identify them using signals they send. Signals used for identification are impacted by a wireless channel and receiver circuitry, creating additional impairments that can confuse transmitter identification. Eliminating these impairments or just evaluating them, requires data captured over a prolonged period of time, using many spatially separated transmitters and receivers. In this paper, we present WiSig; a large-scale WiFi dataset containing 10 million packets captured from 174 off-the-shelf WiFi transmitters and 41 USRP receivers over 4 captures spanning a month. WiSig is publicly available, not just as raw captures, but as conveniently pre-processed subsets of limited size, along with the scripts and examples. A preliminary evaluation performed using WiSig shows that changing receivers, or using signals captured on a different day can significantly degrade a trained classifier's performance. While capturing data over more days or more receivers limits the degradation, it is not always feasible, and novel data-driven approaches are needed. WiSig provides the data to develop and evaluate these approaches towards channel and receiver agnostic transmitter fingerprinting.INDEX TERMS RF fingerprinting, transmitter identification, WiFi dataset I. INTRODUCTION

show abstract

Section: Impact Of Number Of Transmittersmentioning

confidence: 99%

“…This dataset was used by many works [1], [10], [11]; however, it is not publicly accessible. In our previous work [12], we considered a WiFi dataset using 163 WiFi transmitters captured in the Orbit testbed [13], but it only considered one receiver. The previously discussed datasets are summarized in Table 1.…”

mentioning

confidence: 99%

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In reality, however, it is impossible to obtain all potential devices in advance when training a classifier since the number of devices in the system is unlikely to remain unchanged -a problem known as openset authentication [34]. An obvious solution is to retrain the classifier whenever a new device enters the system [35], [36]. While this approach is theoretically sound, it may incur huge system resources (e.g., time, energy) in a practical deployment.…”

Section: B Open-set Physical Layer Authenticationmentioning

confidence: 99%

A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication

Xie

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

Radio-frequency fingerprints (RFFs) are promising solutions for realizing low-cost physical layer authentication. Machine learning-based methods have been proposed for RFF extraction and discrimination. However, most existing methods are designed for the closed-set scenario where the set of devices is remains unchanged. These methods can not be generalized to the RFF discrimination of unknown devices. To enable the discrimination of RFF from both known and unknown devices, we propose a new end-to-end deep learning framework for extracting RFFs from raw received signals. The proposed framework comprises a novel preprocessing module, called neural synchronization (NS), which incorporates the datadriven learning with signal processing priors as an inductive bias from communication-model based processing. Compared to traditional carrier synchronization techniques, which are static, this module estimates offsets by two learnable deep neural networks jointly trained by the RFF extractor. Additionally, a hypersphere representation is proposed to further improve the discrimination of RFF. Theoretical analysis shows that such a data-and-model framework can better optimize the mutual information between device identity and the RFF, which naturally leads to better performance. Experimental results verify that the proposed RFF significantly outperforms purely data-driven DNNdesign and existing handcrafted RFF methods in terms of both discrimination and network generalizability.

show abstract

Section: Introductionmentioning

confidence: 99%

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

Hanna¹,

Karunaratne²,

Čabrić³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

RF fingerprinting leverages circuit-level variability of transmitters to identify them using signals they send. Signals used for identification are impacted by a wireless channel and receiver circuitry, creating additional impairments that can confuse transmitter identification. Eliminating these impairments or just evaluating them, requires data captured over a prolonged period of time, using many spatially separated transmitters and receivers. In this paper, we present WiSig; a large scale WiFi dataset containing 10 million packets captured from 174 off-theshelf WiFi transmitters and 41 USRP receivers over 4 captures spanning a month. WiSig is publicly available, not just as raw captures, but as conveniently pre-processed subsets of limited size, along with the scripts and examples. A preliminary evaluation performed using WiSig shows that changing receivers, or using signals captured on a different day can significantly degrade a trained classifier's performance. While capturing data over more days or more receivers limits the degradation, it is not always feasible and novel data-driven approaches are needed. WiSig provides the data to develop and evaluate these approaches towards channel and receiver agnostic transmitter fingerprinting.

show abstract

Open Set Wireless Transmitter Authorization: Deep Learning Approaches and Dataset Considerations

Cited by 66 publications

References 46 publications

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

Contact Info

Product

Resources

About