Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG
Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG-2021
Increasingly smart techniques for counterfeiting face and fingerprint traits have increased the potential threats to information security systems, creating a substantial demand for improved security and better privacy and identity protection. The internet of Things (IoT)-driven fingertip electrocardiogram (ECG) acquisition provides broad application prospects for ECG-based identity systems. This study focused on three major impediments to fingertip ECG: the impact of variations in acquisition status, the high computational complexity of traditional convolutional neural network (CNN) models and the feasibility of model migration, and a lack of sufficient fingertip samples. Our main contribution is a novel fingertip ECG identification system that integrates transfer learning and a deep CNN. The proposed system does not require manual feature extraction or suffer from complex model calculations, which improves its speed, and it is effective even when only a small set of training data exists. Using 1200 ECG recordings from 600 individuals, we consider 5 simulated yet potentially practical scenarios. When analyzing the overall training accuracy of the model, its mean accuracy for the 540 chest- collected ECG from PhysioNet exceeded 97.60 %, and for 60 subjects from the CYBHi fingertip-collected ECG, its mean accuracy reached 98.77 %. When simulating a real-world human recognition system on 5 public datasets, the validation accuracy of the proposed model can nearly reach 100 % recognition, outperforming the original GoogLeNet network by a maximum of 3.33 %. To some degree, the developed architecture provides a reference for practical applications of fingertip-collected ECG-based biometric systems and for information network security.
Keywords: Off-the-person | Fingertip ECG biometric | Human identification | Convolutional neural network (CNN) | Transfer learning
Digital Livestock Farming
As the global human population increases, livestock agriculture must adapt to provide more livestock products and with improved efficiency while also addressing concerns about animal welfare, environmental sustainability, and public health. The purpose of this paper is to critically review the current state of the art in digitalizing animal agriculture with Precision Livestock Farming (PLF) technologies, specifically biometric sensors, big data, and blockchain technology. Biometric sensors include either noninvasive or invasive sensors that monitor an individual animal’s health and behavior in real time, allowing farmers to integrate this data for population-level analyses. Real-time information from biometric sensors is processed and integrated using big data analytics systems that rely on statistical algorithms to sort through large, complex data sets to provide farmers with relevant trending patterns and decision-making tools. Sensors enabled blockchain technology affords secure and guaranteed traceability of animal products from farm to table, a key advantage in monitoring disease outbreaks and preventing related economic losses and food-related health pandemics. Thanks to PLF technologies, livestock agriculture has the potential to address the abovementioned pressing concerns by becoming more transparent and fostering increased consumer trust. However, new PLF technologies are still evolving and core component technologies (such as blockchain) are still in their infancy and insufficiently validated at scale. The next generation of PLF technologies calls for preventive and predictive analytics platforms that can sort through massive amounts of data while accounting for specific variables accurately and accessibly. Issues with data privacy, security, and integration need to be addressed before the deployment of multi-farm shared PLF solutions be- comes commercially feasible. Implications Advanced digitalization technologies can help modern farms optimize economic contribution per animal, reduce the drudgery of repetitive farming tasks, and overcome less effective isolated solutions. There is now a strong cultural emphasis on reducing animal experiments and physical contact with animals in-order-to enhance animal welfare and avoid disease outbreaks. This trend has the potential to fuel more research on the use of novel biometric sensors, big data, and blockchain technology for the mutual benefit of livestock producers, consumers, and the farm animals themselves. Farmers’ autonomy and data-driven farming approaches compared to experience-driven animal manage- ment practices are just several of the multiple barriers that digitalization must overcome before it can become widely implemented.
Keywords: Precision Livestock Farming | digitalization | Digital Technologies in Livestock Systems | sensor technology | big data | blockchain | data models | livestock agriculture
A cancelable biometric authentication system based on feature-adaptive random projection
یک سیستم احراز هویت بیومتریک قابل لغو بر اساس طرح تصادفی سازگار با ویژگی-2021
Biometric template data protection is critical in preventing user privacy and identity from leakage. Random projection based cancelable biometrics is an efficient and effective technique to achieve biometric template protection. However, traditional random projection based cancelable template design suffers from the attack via record multiplicity (ARM), where an adversary obtains multiple transformed templates from different applica- tions and the associated parameter keys so as to assemble them into a full-rank linear equation system, thereby retrieving the original feature vector. To address this issue, in this paper we propose a feature-adaptive random projection based method, in which the projection matrixes, the key to the ARM, are generated from one basic matrix in conjunction with local feature slots. The generated projection matrixes are discarded after use, thus making it difficult for the adversary to launch the ARM. Moreover, the random projection in the proposed method is performed on a local-feature basis. This feature-adaptive random projection can mitigate the negative impact of biometric uncertainty on recognition accuracy, as it limits the error to part of the transformed feature vector rather than the entire vector. The proposed method is evaluated on four public available databases FVC2002 DB1-DB3 and FVC2004 DB2. The experimental results and security analysis show the validity of the proposed method.
Keywords: Biometric authentication | Template protection | Random projection | Cancelable biometrics
ECB2: A novel encryption scheme using face biometrics for signing blockchain transactions
ECB2: یک طرح رمزگذاری جدید با استفاده از بیومتریک چهره برای امضای تراکنش های بلاک چین-2021
Blockchain is the technology on the basis of the recent smart and digital contracts. It ensures at this system the required characteristics to be effectively applied. In this work, we propose a novel encryption scheme specifically built to authorize and sign transactions in digital or smart contracts. The face is used as a biometric key, encoded through the Convolutional Neural Network (CNN), FaceNet. Then, this encoding is fused with an RSA key by using the Hybrid Information Fusion algorithm (BNIF). The results show a combined key that ensures the identity of the user that is executing the transaction by preserving privacy. Experiments reveal that, even in strong heterogeneous acquisition conditions for the biometric trait, the identity of the user is ensured and the contract is properly signed in less than 1.86 s. The proposed ECB2 encryption scheme is also very fast in the user template creation (0.05s) and requires at most four attempts to recognize the user with an accuracy of 94%.
Supply chain financial service management system based on block chain IoT data sharing and edge computing
سیستم مدیریت خدمات مالی زنجیره تامین مبتنی بر اشتراک داده های اینترنت اشیا زنجیره بلاکچین و محاسبات لبه ای-2021
The implementation of the ‘‘Internet +” policy advocated by the state has also led to rapid development of Internet finance. In order to promote changes in business development models, as a pioneering work for banks serving the real economy, supply chains are being developed to address small and medium-sized enterprises. The financing of enterprises, the transformation and development needs of banks themselves, and the promotion of logistics technology. Edge computing refers to an open platform that integrates network, data processing, storage and application core functions, and can provide the closest end-of-page service near the object data source to meet real-time, application intelligence, security and privacy Sexual needs. The core of supply chain financing is to establish an optimized plan that can effectively control supply chain financing. By integrating the financing literature of the supply chain, the settlement cost in the supply chain can be solved. Based on theoretical research, this article analyzes supply chain financing and block chain technology. Combined with the current specific situation of block chain in supply chain financing, the management system, cash flow of the supply chain, and risk control system are analyzed. All parties to the supply chain financing optimize the supply chain financing risk control system while reducing business costs and improving corporate efficiency, which greatly reduces the risks of all parties in the supply chain financing. The block chain Iota environment based on shared data and advanced data processing has very powerful theoretical and practical significance for promoting the development of commercial banks and enterprises.
KEYWORDS: Block chain | Internet of things | Edge computing | Supply chain finance | Commercial bank
Ann trained and WOA optimized feature-level fusion of iris and fingerprint
بهینه سازی شبکههای عصبی مصنوعی و WOA آموزش دیده همجوشی در سطح ویژگی عنبیه و اثر انگشت-2021
‘‘Uni Uni-modal Biometric systems has been widely implemented for maintaining security and privacy in various applications like mobile phones, banking apps, airport access control, laptop login etc. Due to Advancement in technologies, imposters designed various ways to breach the security and most of the designed biometric applications security can be compromised. The quality of input sample also play an important role to attain the best performance in terms of improved accuracy and reduced FAR & FRR. Researchers has combined the various biometrics modalities to overcome the problems of Uni-modal bio- metrics. In this paper, a multi biometric feature level fusion system of Iris, and Fingerprint is presented. Due to consistency feature of fingerprint and stability feature of iris modality taken into consideration for high security applications. At pre-processing level, the atmospheric light adjustment algorithm is applied to improve the quality of input samples (Iris and Fingerprint). For feature extraction, the nearest neighbor algorithm and speedup robust feature (SURF) is applied to fingerprint and Iris data respectively. Further, for selecting the best features, the extracted features are optimized by GA algorithm. To achieve an excellent recognition rate, the iris and fingerprint data is trained by ANN algorithm. The experimental results show that the proposed system exhibits the improved performance and better security. Finally, the template is secured by applying the AES algorithm and results are compared with DES, 3DES, RSA and RC4 algorithm.© 2021 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the 1st International Con- ference on Computations in Materials and Applied Engineering – 2021.
Keywords: Multimodal biometrics fusion | ANN | SURF | GA | RSA
Learning from learning: detecting account takeovers by identifying forgetful users
یادگیری از یادگیری: شناسایی حساب های حساب با شناسایی کاربران فراموش شده-2021
Credential-stuffing attacks are increasing in frequency, allowing threat actors to use data breaches from one source to perpetrate another. While multi-factor authentication remains a crucial preventative measure to protect against credential stuffing, the availability of credential data sets with contact information and the correlation with demographic data can allow threat actors to overcome it through interactive social engineering. Concurrently, alternative defence mechanisms such as network source profiling and device fingerprinting lose effectiveness as privacy-protecting technologies reduce the observable variability between legitimate and fraudulent user sessions.
GaitCode: Gait-based continuous authentication using multimodal learning and wearable sensors
GaitCode: احراز هویت پیوسته مبتنی بر راه رفتن با استفاده از یادگیری چند حالته و حسگرهای پوشیدنی-2021
The ever-growing threats of security and privacy loss from unauthorized access to mobile devices have led to the development of various biometric authentication methods for easier and safer data access. Gait-based authentication is a popular biometric authentication as it utilizes the unique patterns of human locomotion and it requires little cooperation from the user. Existing gait-based biometric authentication methods however suffer from degraded performance when using mobile devices such as smart phones as the sensing device, due to multiple reasons, such as increased accelerometer noise, sensor orientation and positioning, and noise from body movements not related to gait. To address these drawbacks, some researchers have adopted methods that fuse information from multiple accelerometer sensors mounted on the human body at different lo- cations. In this work we present a novel gait-based continuous authentication method by applying multimodal learning on jointly recorded accelerometer and ground contact force data from smart wearable devices. Gait cycles are extracted as a basic authentication element, that can continuously authenticate a user. We use a network of auto-encoders with early or late sensor fusion for feature extraction and SVM and soft max for classification. The effectiveness of the proposed approach has been demonstrated through extensive experiments on datasets collected from two case studies, one with commercial off-the-shelf smart socks and the other with a medical-grade research prototype of smart shoes. The evaluation shows that the proposed approach can achieve a very low Equal Error Rate of 0.01% and 0.16% for identification with smart socks and smart shoes respectively, and a False Acceptance Rate of 0.54%–1.96% for leave-one-out authentication.
Keywords: Biometric authentication | Gait authentication | Autoencoders | Sensor fusion | Multimodal learning | Wearable sensors
Multimodal biometric authentication for mobile edge computing
Multimodal biometric authentication for mobile edge computing-2021
In this paper, we describe a novel Privacy Preserving Biometric Authentication (PPBA) sys- tem designed for Mobile Edge Computing (MEC) and multimodal biometrics. We focus on hill climbing attacks that reveal biometric templates to insider adversaries despite the encrypted storage in the cloud. First, we present an impossibility result on the existence of two-party PPBA systems that are resistant to these attacks. To overcome this negative result, we add a non-colluding edge server for detecting hill climbing attacks both in semi-honest and malicious model. The edge server that stores each user’s secret parameters enables to outsource the biometric database to the cloud and perform matching in the encrypted domain. The proposed system combines Set Overlap and Euclidean Distance metrics using score level fusion. Here, both the cloud and edge servers cannot learn the fused matching score. Moreover, the edge server is prevented from accessing any partial score. The efficiency of the crypto-primitives employed for each biometric modality results in linear computation and communication overhead. Under different MEC scenarios, the new system is found to be most efficient with a 2-tier architecture, which achieves %75 lower latency compared to mobile cloud computing.© 2021 Elsevier Inc. All rights reserved.
Keywords: Privacy Preserving Biometric Authentication (PPBA) | Mobile Edge Computing (MEC) | Multimodal Biometrics | Hill Climbing Attacks (HCA) | Euclidean distance | Malicious security
Secure and verifiable iris authentication system using fully homomorphic encryption
سیستم تأیید هویت عنبیه امن و قابل تأیید با استفاده از رمزگذاری کاملاً همگون-2021
With the escalated usage of a biometric authentication system (BAS), template protection for biometrics attracted research interest in recent years. The assumption behind the existing homomorphic encryption-based BASs is that the server performs the computations honestly. In a malicious server setting, the server may return an arbitrary result to save the computational resources, which may result in false accept/reject. To tackle this challenge, we propose a secure and verifiable classification based iris authentication system (SvaS). SvaS aims to achieve both privacy-preserving (PP) training and PP classification of Nearest Neighbor and Multi-class Perceptron models. The Fan-vercauteren scheme provides confidentiality for the iris templates, and aggregate verification vector helps to verify the correctness of the computed classification result. Extensive experimental results on benchmark iris databases demonstrate that SvaS provides privacy to the iris templates with no loss in accuracy and eliminates the need to trust the server.
Keywords: Biometrics | Privacy-preserving | Homomorphic encryption | Multi-class Perceptron | Nearest Neighbor