In this paper, a mm-Wave chipless RFID tag is developed to operate in the V-band for authentication applications. A novel approach based on tag backscattered E-field measurements at different orientation angles for unitary classification is proposed. The concept is based on the hardness to identically reproduce materials due to the inherent randomness in the fabrication process. These uncertainties are transcribed in very small variations that can be observed in the tag electromagnetic response. A set of 16 identical tags were fabricated, each tag shares same fabrication mask and manufacture process method. Spatial diversity using the tag backscattering pattern (at two different angles) adds independent characteristics for estimating authenticity of each tag. To better exploit the large amount of data collect with this approach, a Machine Learning (ML) sighting classification is used, which enhance the system performance. The probability of error (PE) achieved with the method is around 1%. This PE is four times lower than the one obtained with a similar approach implemented in the X-band.

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.

This paper presents a millimeter-wave chipless RFID tag for authentication applications. The concept is based on the idea that it is extremely difficult to identically reproduce materials that inherently have a random aspect due to manufacturing process variations. This paper introduces the paradigm of millimeter-wave authentication based on tags without any chip, including an identifier capable of communicating in the millimeter-wave range. For this purpose, millimeter-wave chipless tags without a ground plane are designed using the RF Encoding Particle (REP) technique. This approach establishes a relation between the geometrical parameters of the isolated scatter and its electromagnetic signature. An elementary particle multiplication strategy is envisaged to increase the backscattered tag level. The evaluated probability of error around 17% is reached with a fabricated tag set from the same manufacturer simultaneously. This probability is two times lower than the one obtained with a similar approach implemented in the X-band.