Dickson Akuoko Sarpong

arXiv2026

CADRE: Card-Agnostic Domain-Aligned RF Embeddings for Virtual PIN Pads on Passive NFC Cards

Near Field Communication (NFC) cards are widely used for identification, but their passive nature often limits the ability to incorporate additional security mechanisms. As a result, anyone holding the card may be incorrectly recognized as an authenticated user. To overcome this limitation, this paper presents a secure manual password input framework using a virtual PIN pad for passive NFC cards. Users input passwords by pressing designated regions on the card, which induces measurable impedance variations in the NFC antenna. These variations change the RF signals subtly, and a deep learning model is used to infer the intended password from the resulting signal patterns. A key challenge is that identical press interactions can produce significantly different responses across NFC cards, which yields unreliable recognition. To address this, we introduce a lightweight recognition approach that operates directly within the RF feature space at the penultimate layer of a temporal neural encoder. An adversarial domain-alignment module reshapes virtual PIN pad press-response embeddings into compact, card-invariant clusters, which enables stable and consistent recognition across heterogeneous cards. To support model training and evaluation, a reconfigurable software-defined radio (SDR) testbed is developed, and PIN pad press-response data are collected from commercially available ISO/IEC 15693 cards. Recognition is performed using a Mahalanobis distance metric derived from a calibration-based covariance model that captures feature correlations. Experimental results show that the proposed system achieves a 98.20\% recognition acceptance rate and remains robust under substantial noise degradation. The framework is fully card-agnostic and can be seamlessly integrated into existing NFC infrastructures.

eess.SP↗

arXiv2025

Model-Agnostic Uncertainty Quantification for Fast NFC Tag Identification using RF Fingerprinting

Near Field Communication (NFC) is widely used in security applications such as door access systems and ID cards. However, clone attacks can replicate digital information, enabling unauthorized access. RF fingerprinting offers a robust defense by extracting unique physical-layer features from NFC cards that cannot be cloned. While RF fingerprinting has been extensively applied to Internet of Things (IoT) device authentication, NFC tags present distinct characteristics that require specialized approaches. This paper focuses on RF fingerprinting for the ISO15693 NFC tag, which is a widely used international standard, by leveraging multi-channel, multi-rate data sampling to enhance accuracy. Deep learning and Random Forest models are employed to identify NFC tags, while uncertainty quantification, particularly Conformal Prediction, accelerates the identification process with high confidence and precision. A software-defined radio (SDR) testbed is developed to transmit customized commands and collect multi-channel multi-rate NFC signals. The multi-channel multi-rate NFC signals are progressively collected to ensure fast and accurate identification. Experimental results demonstrate that the proposed system achieves high accuracy by adaptively utilizing the optimal combination of NFC signals. The developed solution is model-agnostic which can be utilized for any machine learning-based NFC tag identification.

eess.SP↗