Fingerprint authentication is extensively adopted due to its ease of capture, low cost sensors and high recognition accuracy. The Minutia Cylinder Code (MCC) is a high-quality feature representation widely used in fingerprint authentication. However, there are two main limitations in the direct use of MCC: redundancy in the feature representation due to overlap between minutiae vicinities, which can lead to inefficient resource utilization; and vulnerability to template inversion attacks, which may expose the original fingerprint data and threaten user privacy. In this paper, we propose a lightweight privacy-preserving fingerprint authentication system that overcomes these limitations through two novel algorithms. The first algorithm, P-MCC, uses the Pearson correlation coefficient to prune MCC features to effectively reduce redundancy and improve resource utilisation, yielding a lightweight design. The second algorithm, S-MCC, applies a secure Boolean function which transforms the pruned MCC features non-invertibly to ensure privacy, thus preventing the reconstruction of original fingerprint data. Together, P-MCC and S-MCC provide a lightweight privacy-preserving fingerprint authentication system, which is well suited to resource-constrained environments, such as the Internet of Things (IoT). Experimental results demonstrate the effectiveness of the proposed system and its practicality in IoT applications.

Face recognition offers seamless human-machine interaction and efficiency. However, its widespread adoption has heightened security and privacy concerns due to the risks associated with compromised biometric data, such as spoofing and unauthorized tracking. To mitigate these concerns, this paper introduces a novel privacy-preserving face recognition framework that integrates an enhanced dual-path feature compression approach with homomorphic encryption (HE) for secure and efficient authentication. We leverage the robust deep neural network model FaceNet to extract discriminative 512-dimensional feature vectors and propose two significantly improved complementary feature compression methods tailored specifically for encrypted biometric systems: (1) Partitioned Principal Component Analysis (P-PCA), which employs a novel segment-wise PCA transformation, preserving localized discriminative information and supporting revocable biometric templates; and (2) Segment-wise Locality-Sensitive Hashing (S-LSH), introducing segment-specific hashing optimized for efficient binary representation and privacy-preserving encrypted-domain computations. Both compressed real-valued and binary features are securely encrypted using HE, enabling direct encrypted-domain similarity computations without exposing sensitive biometric data. Extensive experiments demonstrate that our method achieves competitive authentication performance while maintaining computational efficiency and practical feasibility.

As artificial intelligence continues to drive advancements in computer vision, particularly in areas such as image analysis, object detection, and facial recognition, the ability to accurately recognize patterns in visual data has become a central focus of research. However, alongside these advances, concerns about the privacy risks associated with the training data used in AI models have also gained prominence. Deep learning models, frequently employed in computer vision tasks, can unintentionally expose sensitive information from the data they are trained on, raising the need for comprehensive research into privacy-preserving techniques. This paper explores the intersection of AI-driven pattern recognition and the privacy risks involved in training models on image data. Existing studies show that attackers can exploit the gradients from deep learning processes to reconstruct original image data, including personal and identifiable information, such as facial features. By iteratively adjusting input data, attackers can minimize the difference between the gradients of the random and stolen data, leading to the full reconstruction of private images. Current privacy protection methods fall short of explaining the relationship between an attacker’s capacity to recover visual data and the structure of the targeted model. This paper introduces a novel privacy auditing framework that directly assesses the extent to which gradient-based attacks can reconstruct sensitive data. Unlike traditional methods, which mainly focus on mitigating privacy risks through model regularization or data obfuscation, our approach provides a systematic and quantitative evaluation of gradient leakage, filling a critical gap in existing privacy protection techniques. This paper investigates the relationships among reconstructed data, model gradients, and the original input data in the context of computer vision. By formalizing the connection between gradient similarity and data similarity, we propose a novel methodology that quantifies the vulnerability of deep learning models to data reconstruction attacks. Building on these insights, we propose a novel privacy auditing method aimed at evaluating the privacy risks associated with deep learning models used in pattern recognition for image data.

Authentication plays an essential role in securing the communication between sensor nodes within a wireless body sensor network (WBSN). The electrocardiogram (ECG) as a type of physiological data collected by sensor nodes in WBSNs can provide intrinsic liveness detection and the ECG data are continuously available. These are highly desirable properties for authentication purposes. Although ECG-based intranode authentication for WBSNs has been extensively studied, far less attention is paid for protecting the ECG data despite their sensitivity. In this article, we propose a privacy-preserving ECG-based authentication system using a noninvertible transformation scheme called manipulatable Haar transform (MHT). The proposed authentication system not only provides secure intranode authentication for WBSNs but also protects the sensitive health and identity information contained in ECG data from being exposed to adversaries. The experiment results on two public databases and a real Internet of Things device show the strong performance and efficiency of the proposed system. Moreover, security analysis demonstrates the validity of the MHT.

Privacy protection in electronic healthcare applications is an important consideration due to the sensitive nature of personal health data. Internet of Health Things (IoHT) networks have privacy requirements within a healthcare setting. However, these networks have unique challenges and security requirements (integrity, authentication, privacy and availability) must also be balanced with the need to maintain efficiency in order to conserve battery power, which can be a significant limitation in IoHT devices and networks. Data are usually transferred without undergoing filtering or optimization, and this traffic can overload sensors and cause rapid battery consumption when interacting with IoHT networks. This consequently poses restrictions on the practical implementation of these devices. As a solution to address the issues, this paper proposes a privacy-preserving two-tier data inference framework - this can conserve battery consumption by reducing the data size required to transmit through inferring the sensed data and can also protect the sensitive data from leakage to adversaries. Results from experimental evaluations on privacy show the validity of the proposed scheme as well as significant data savings without compromising the accuracy of the data transmission, which contributes to energy efficiency of IoHT sensor devices.

With built-in artificial intelligence (AI), edge devices, e.g., smart cameras, can perform tasks like detecting and tracking individuals, which is referred to as edge biometrics. As a driving force for AI, machine/deep learning plays a critical role in edge biometrics. Machine/deep learning based edge biometric systems outperform their nonmachine learning counterpart. However, research shows that artificial neural networks, e.g., convolutional neural networks, are invertible such that adversaries can obtain a certain amount of information about the original inputs/templates. This information leakage is not tolerable for biometric systems because biometric data in the original (raw) templates cannot be reset or replaced. Once compromised, they are lost forever. Therefore, how to prevent original biometric templates from being attacked through inverting deep neural networks is a pressing, but unsolved issue, for deep learning based biometric recognition. To address the issue, in this paper, we develop a novel biometric template protection algorithm using the binary decision diagram (BDD) for deep learning based finger-vein biometric systems. The proposed algorithm is capable of creating a new noninvertible version of the original finger-vein template, which is stacked with an artificial neural network-the multilayer extreme learning machine (ML-ELM) to generate a privacy-preserving finger-vein recognition system, named BDD-ML-ELM. The proposed BDD-ML-ELM ensures the safety of the original finger-vein template even if its transformed version is compromised. The transformed template, if compromised, can be revoked and replaced with another new version by simply changing the user-specific keys. Therefore, the BDD-ML-ELM has a clear advantage over the existing machine/deep learning based biometric systems, whose raw biometric templates are vulnerable when the artificial neural network suffers an inversion attack.

Any proposal to provide security for implantable medical devices (IMDs), such as cardiac pacemakers and defibrillators, has to achieve a trade-off between security and accessibility for doctors to gain access to an IMD, especially in an emergency scenario. In this paper, we propose a finger-to-heart (F2H) IMD authentication scheme to address this trade-off between security and accessibility. This scheme utilizes a patient's fingerprint to perform authentication for gaining access to the IMD. Doctors can gain access to the IMD and perform emergency treatment by scanning the patient's finger tip instead of asking the patient for passwords/security tokens, thereby, achieving the necessary trade-off. In the scheme, an improved minutia-cylinder-code-based fingerprint authentication algorithm is proposed for the IMD by reducing the length of each feature vector and the number of query feature vectors. Experimental results show that the improved fingerprint authentication algorithm significantly reduces both the size of messages in transmission and computational overheads in the device, and thus, can be utilized to secure the IMD. Compared to existing electrocardiogram signal-based security schemes, the F2H scheme does not require the IMD to capture or process biometric traits in every access attempt since a fingerprint template is generated and stored in the IMD beforehand. As a result, the scarce resources in the IMD are conserved, making the scheme sustainable as well as energy efficient.

Smart mobile devices are playing a more and more important role in our daily life. Cancelable biometrics is a promising mechanism to provide authentication to mobile devices and protect biometric templates by applying a noninvertible transformation to raw biometric data. However, the negative effect of nonlinear distortion will usually degrade the matching performance significantly, which is a nontrivial factor when designing a cancelable template. Moreover, the attacks via record multiplicity (ARM) present a threat to the existing cancelable biometrics, which is still a challenging open issue. To address these problems, in this paper, we propose a new cancelable fingerprint template which can not only mitigate the negative effect of nonlinear distortion by combining multiple feature sets, but also defeat the ARM attack through a proposed feature decorrelation algorithm. Our work is a new contribution to the design of cancelable biometrics with a concrete method against the ARM attack. Experimental results on public databases and security analysis show the validity of the proposed cancelable template.

Apple claims that iPhone 6, which is equipped with iOS 8.0 and later version, is secure enough to prevent a user's private data from law enforcement or malicious intruders. In pre-iOS 8.0 operating systems, a user's data were only encrypted by hardware-based keys, which can be obtained by Apple. But in iOS 8.0 and later version, the private data on the iPhone are protected by a secret key that is protected by the user's passcode, which the Apple does not hold. In this paper, supported by real-life experiments, we demonstrate that several vulnerabilities of iPhone 6 with iOS 8, which are brought by ordinary user operations, can lead to the leakage of the private data. Then we conduct vulnerability analysis and give the reasons that cause these vulnerabilities from a technical perspective. Meanwhile, experiments of forging attack aiming at iPhone 6 Touch ID are conducted.

Although some nice properties of the Delaunay triangle-based structure have been exploited in many fingerprint authentication systems and satisfactory outcomes have been reported, most of these systems operate without template protection. In addition, the feature sets and similarity measures utilized in these systems are not suitable for existing template protection techniques. Moreover, local structural change caused by nonlinear distortion is often not considered adequately in these systems. In this paper, we propose a Delaunay quadrangle-based fingerprint authentication system to deal with nonlinear distortion-induced local structural change that the Delaunay triangle-based structure suffers. Fixed-length and alignment-free feature vectors extracted from Delaunay quadrangles are less sensitive to nonlinear distortion and more discriminative than those from Delaunay triangles and can be applied to existing template protection directly. Furthermore, we propose to construct a unique topology code from each Delaunay quadrangle. Not only can this unique topology code help to carry out accurate local registration under distortion, but it also enhances the security of template data. Experimental results on public databases and security analysis show that the Delaunay quadrangle-based system with topology code can achieve better performance and higher security level than the Delaunay triangle-based system, the Delaunay quadrangle-based system without topology code, and some other similar systems.

Bio-cryptography is a new security technology which combines cryptography with biometrics. Fuzzy extractors are effective in terms of binding a cryptographic key to biometric features. However, most existing fuzzy extractors require fingerprint registration prior to the application of fuzzy extractors, and depend on error-correction codes to rectify the biometric uncertainty. This is not operative in practice due to low matching performance. In this paper, by taking full advantage of a Delaunay triangulation net, e.g. local structural stability, we propose a new registration-free Delaunay triangle-based fuzzy extractor. The new fuzzy extractor not only can mitigate biometric uncertainty but also eliminate the feature pre-alignment process in fingerprint authentication. Experimental results show that the proposed scheme achieves a better performance than those of the those of existing registration-based fuzzy extractor methods.