Privacy-Preserving Fast Three-Factor Authentication and Key Agreement for IoT-Based E-Health Systems

Electronic healthcare (e-health) systems have received renewed interest, particularly in the current COVID-19 pandemic (e.g., lockdowns and changes in hospital policies due to the pandemic). However, ensuring security of both data-at-rest and data-in-transit remains challenging to achieve, particularly since data is collected and sent from less insecure devices (e.g., patients' wearable or home devices). While there have been a number of authentication schemes, such as those based on three-factor authentication, to provide authentication and privacy protection, a number of limitations associated with these schemes remain (e.g., (in)security or computationally expensive). In this study, we present a privacy-preserving three-factor authenticated key agreement scheme that is sufficiently lightweight for resource-constrained e-health systems. The proposed scheme enables both mutual authentication and session key negotiation in addition to privacy protection, with minimal computational cost. The security of the proposed scheme is demonstrated in the Real-or-Random model. Experiments using Raspberry Pi show that the proposed scheme achieves reduced computational cost (of up to 89.9% in comparison to three other related schemes).

Cyber-physical customer management for internet of robotic things-enabled banking

In-person banking is still an important part of financial services around the world. Hybrid bank branches with service robots can improve efficiency and reduce operating costs. An efficient autonomous Know-Your-Customer (KYC) is required for hybrid banking. In this paper, an automated deep learning-based framework for interbank KYC in robot-based cyber-physical banking is proposed. A deep biometric architecture was used to model the customer’s KYC and anonymise the collected visual data to ensure the customer’s privacy. The symmetric-asymmetric encryption-decryption module in addition to the blockchain network was used for secure and decentralized transmission and validation of the biometric information. A high-capacity fragile watermarking algorithm based on the integer-to-integer discrete wavelet transform in combination with the Z6 and A6 lattice vector quantization for the secure transmission and storage of in-person banking documents is also proposed. The proposed framework was simulated and validated using a Pepper humanoid robot for the automated biometric-based collection of handwritten bank checks from customers adhering to COVID-19 pandemic safety guidelines. The biometric information of bank customers such as fingerprint and name is embedded as a watermark in the related bank documents using the proposed framework. The results show that the proposed security protection framework can embed more biometric data in bank documents in comparison with similar algorithms. Furthermore, the quality of the secured bank documents is 20% higher in comparison with other proposed algorithms. Also, the hierarchal visual information communication and storage module that anonymizes the identity of people in videos collected by robots can satisfy the privacy requirements of the banks. Overall, the proposed framework can provide a rapid, efficient, and cost-effective inter-bank solution for future in-person banking while adhering to the security requirements and banking regulations. Author

Completely Contactless and Online Finger Knuckle Identification for Real World Applications

Completely contactless and at-a-distance personal identification provides enhanced user convenience, and improved hygiene and is highly sought under the COVID-19 pandemic. This paper proposes an accurate and generalizable deep neural network-based framework for the ‘completely’contactless finger knuckle identification. We design and introduce a new loss function to enable a fully convolutional network to more effectively learn knuckle features that are imaged under at-a-distance imaging. A ‘completely’contactless system also requires efficient online finger knuckle detection capabilities. This paper, for the first time in our knowledge, develops and introduces accurate capabilities to efficiently detect and segment finger knuckle patterns from images with complex backgrounds as widely observed in real-world applications. We introduce angular loss to accurately predict oriented knuckle patterns and incorporate into our framework. Experimental results presented in this paper on five different public databases, using challenging protocols and cross-database performance evaluation, illustrate outperforming results and validate the effectiveness of the proposed framework for completely contactless applications. IEEE

Apple in My Eyes (AIME): Liveness Detection for Mobile Security Using Corneal Specular Reflections

The demand for contactless biometric authentication has significantly increased during the COVID-19 pandemic and beyond to prevent the spread of Coronavirus. The global pandemic unexpectedly affords a greater opportunity for contactless authentication, but iris and facial recognition biometrics have many usability, security, and privacy challenges, including mask-wearing and presentation attacks (PAs). Mainly, liveness detection against spoofing is notably a challenging task as various biometric authentication methods cannot efficiently assess the real user's physical presence in unsupervised environments. Although several face anti-spoofing methods have been proposed using add-on sensors, dynamic facial texture features, and 3-D mapping, most of them require expensive sensors and substantial computational resources, or fail to detect sophisticated 3-D face spoofing. This article presents a software-based facial liveness detection method named Apple in My Eyes (AIME). AIME is intended to detect the liveness against spoofing for mobile device security using challenge-response testing. AIME generates various screen patterns as authentication challenges, then passively detects corneal-specular reflection responses from human eyes using a frontal camera and analyzes the detected reflections using lightweight machine learning techniques. AIME system components include challenge and pattern detection, feature extraction and classification, and data augmentation and training. We have implemented AIME as a cross-platform application compatible with Android, iOS, and the Web. Our comprehensive experimental results reveal that AIME detects liveness with high accuracy at around 200-ms against different types of sophisticated PAs. AIME can also efficiently detect liveness in multiple contactless biometric authentications without any costly extra sensors nor involving users' active responses.

M2FRED: Mobile Masked Face REcognition through periocular Dynamics analysis

Recent regulations to block the widespread transmission of COVID-19 disease among people impose the use of facial masks indoor and outdoor. Such restriction becomes critical in all those scenarios where access controls take benefit from biometric recognition systems. The occlusions due to the presence of a facial mask make a significant portion of human faces unavailable for feature extraction and analysis. This work explores the contribution of the solely periocular region of the face to achieve a robust recognition approach suitable for mobile devices. Rather than working on a static analysis of the facial features, like largely done by work on periocular recognition in the literature, the proposed study focuses the attention on the analysis of face dynamics so that the spatio-temporal features make the recogniser frame-independent and tolerant to user movements during the acquisition. To obtain a lightweight processing, which is compliant with limited computing power of mobile devices, the spatio-temporal representation of the periocular region has analysed and classified through Machine Learning approaches. The experimental discussion has been performed on a new dataset, Mobile Masked Face REcognition Database, specifically designed to analyse the periocular region dynamics in presence of facial masks. For a wider comparative analysis, a publicly available dataset called XM2VTS has been considered as well as Deep Learning solutions have been experimented to discuss the challenging aspects of the recognition problem. Moreover, a summary of the state-of-the-art on periocular recognition driven by COVID pandemic has been presented, showing how the research efforts in this field focused on recognition of still images. Experimental results show promising levels of performance as well as limitations of the proposed approach, creating the premises for future directions. Author

Privacy-Preserving Fast Authentication and Key Agreement for E-health Systems in IoT, based on Three-Factor Authentication

Electronic healthcare (e-health) systems have received renewed interest, particularly in the current COVID-19 pandemic (e.g., lockdowns and changes in hospital policies due to the pandemic). However, ensuring security of both data-at-rest and data-in-transit remains challenging to achieve, particularly since data is collected and sent from less insecure devices (e.g., patients wearable or home devices). While there have been a number of authentication schemes, such as those based on three-factor authentication, to provide authentication and privacy protection, a number of limitations associated with these schemes remain (e.g., (in)security or computationally expensive). In this study, we present a privacy-preserving three-factor authenticated key agreement scheme that is sufficiently lightweight for resource-constrained e-health systems. The proposed scheme enables both mutual authentication and session key negotiation in addition to privacy protection, with minimal computational cost. The security of the proposed scheme is demonstrated in the Real-or-Random model. Experiments using Raspberry Pi show that the proposed scheme achieves reduced computational cost (of up to 89.9\% in comparison to three other related schemes). IEEE