A New Method of Secure Authentication Based on Electromagnetic Signatures of Chipless RFID Tags and Machine Learning Approaches

Abstract

In this study, we present the implementation of a neural network model capable of classifying radio frequency identification (RFID) tags based on their electromagnetic (EM) signature for authentication applications. One important application of the chipless RFID addresses the counterfeiting threat for manufacturers. The goal is to design and implement chipless RFID tags that possess a unique and unclonable fingerprint to authenticate objects. As EM characteristics are employed, these fingerprints cannot be easily spoofed. A set of 18 tags operating in V band (65–72 GHz) was designed and measured. V band is more sensitive to dimensional variations compared to other applications at lower frequencies, thus it is suitable to highlight the differences between the EM signatures. Machine learning (ML) approaches are used to characterize and classify the 18 EM responses in order to validate the authentication method. The proposed supervised method reached a maximum recognition rate of 100%, surpassing in terms of accuracy most of RFID fingerprinting related work. To determine the best network configuration, we used a random search algorithm. Further tuning was conducted by comparing the results of different learning algorithms in terms of accuracy and loss.

Robust deep learning-based detection and classification system for chipless Arabic RFID letters

“…The frequency-domain chipless tags are available in the form of different geometrical shaped-and letter-based resonators. Some examples of foremost category are tags based on split ring resonators [9,10]; M/U/T/E-Shaped strips [11,12]; slotted patch [13]; nested square loops [14]; space-filling curve shape [15]; slot/stub-loaded patches [16]; and multi-layer patches [17].…”

“…The spectral resonances (electromagnetic signature (EMS)) from the back scattered response of frequency-domain tags are analyzed for their encoding. The convectional approaches involves the analysis of the peaks/dips in the recorded back scattered S-parameters [7,19,12], electric-field [21], and radar cross section (RCS) characteristics [18,6,20,23,24] of designed tags. Figure 1 shows the typical co-and cross-polar RCS characteristics of a chipless Arabic RFID letter tag.…”

“…Figure 1 shows the typical co-and cross-polar RCS characteristics of a chipless Arabic RFID letter tag. The difference in the number of resonances or resonance frequencies in recorded EMS is used to classify the different analyzed tags in [7,19,12,21,18].…”

“…The authors in [11] also used SVM algorithm on the 816 results of 4 T-shaped 2-bit encoding tags for their detection and classification. Nastasiu et al [12] presents a model based on a neural network that can classify the 18 E-shaped RFID tags based on their EM signatures. Table 2 summarizes the recent AI-based studies for the detection and classification of RFID tags.…”

“…Table 2 summarizes the recent AI-based studies for the detection and classification of RFID tags. The compared studies in Table 2 are either for a fixed Latin shape [11,12] or for combinations of Peyote symbols [7] with limited number of alphabets.…”