Face Attribute Convolutional Neural Network System for Data Security with Improved Crypto Biometrics

Due to the enormous usage of the internet for transmission of data over a network, security and authenticity become major risks. Major challenges encountered in biometric system are the misuse of enrolled biometric templates stored in database server. To describe these issues various algorithms are implemented to deliver better protection to biometric traits such as physical (Face, fingerprint, Ear etc.) and behavioural (Gesture, Voice, tying etc.) by means of matching and verification process. In this work, biometric security system with fuzzy extractor and convolutional neural networks using face attribute is proposed which provides different choices for supporting cryptographic processes to the confidential data. The proposed system not only offers security but also enhances the system execution by discrepancy conservation of binary templates. Here Face Attribute Convolutional Neural Network (FACNN) is used to generate binary codes from nodal points which act as a key to encrypt and decrypt the entire data for further processing. Implementing Artificial Intelligence (AI) into the proposed system, automatically upgrades and replaces the previously stored biometric template after certain time period to reduce the risk of ageing difference while processing. Binary codes generated from face templates are used not only for cryptographic approach is also used for biometric process of enrolment and verification. Three main face data sets are taken into the evaluation to attain system performance by improving the efficiency of matching performance to verify authenticity. This system enhances the system performance by 8% matching and verification and minimizes the False Acceptance Rate (FAR), False Rejection Rate (FRR) and Equal Error Rate (EER) by 6 times and increases the data privacy through the biometric cryptosystem by 98.2% while compared to other work.     

基于CNN的改进行人重识别技术

针对行人重识别研究中训练样本的不足,为提高识别精度及泛化能力,提出一种基于卷积神经网络的改进行人重识别方法。首先对训练数据集进行扩充,使用生成对抗网络无监督学习方法生成无标签图像;然后与原数据集联合作半监督卷积神经网络训练,通过构建一个Siamese网络,结合分类模型和验证模型的特点进行训练;最后加入无标签图像类别分布方法,计算交叉熵损失来进行相似度量。实验结果表明,在Market-1501、CUHK03和DukeMTMC-reID数据集上,该方法相比原有的Siamese方法在Rank-1和mAP等性能指标上有近3～5个百分点的提升。当样本较少时,该方法具有一定应用价值。     

Innovative Hetero-Associative Memory Encoder (HAMTE) for Palmprint Template Protection

Many types of research focus on utilizing Palmprint recognition in user identification and authentication. The Palmprint is one of biometric authentication (something you are) invariable during a person’s life and needs careful protection during enrollment into different biometric authentication systems. Accuracy and irreversibility are critical requirements for securing the Palmprint template during enrollment and verification. This paper proposes an innovative HAMTE neural network model that contains Hetero-Associative Memory for Palmprint template translation and projection using matrix multiplication and dot product multiplication. A HAMTE-Siamese network is constructed, which accepts two Palmprint templates and predicts whether these two templates belong to the same user or different users. The HAMTE is generated for each user during the enrollment phase, which is responsible for generating a secure template for the enrolled user. The proposed network secures the person’s Palmprint template by translating it into an irreversible template (different features space). It can be stored safely in a trusted/untrusted third-party authentication system that protects the original person’s template from being stolen. Experimental results are conducted on the CASIA database, where the proposed network achieved accuracy close to the original accuracy for the unprotected Palmprint templates. The recognition accuracy deviated by around 3%, and the equal error rate (EER) by approximately 0.02 compared to the original data, with appropriate performance (approximately 13 ms) while preserving the irreversibility property of the secure template. Moreover, the brute-force attack has been analyzed under the new Palmprint protection scheme.     

基于声学音素向量和孪生网络的二语者发音偏误确认

随着自动大规模语音识别的不断发展,以自动语音识别为基础的计算机辅助发音教学也随之进步,作为传统教学方法的补充,它极大地弥补了传统教育资源不足以及传统教育方法无法及时给学习者反馈的缺陷。二语学习者的发音偏误确认和评价在计算机辅助发音训练中是较为重要的研究课题之一。针对二语者发音偏误的确认任务中缺少二语偏误发音标注问题,该文提出了一种基于声学音素向量和孪生网络的方法,将带有配对信息的成对的语音特征作为系统输入,通过神经网络将语音特征映射到高层表示,期望将不同的音素区分开。训练过程引入了孪生网络,依照输出的两个音素向量是否来自于同一类音素来调整和优化输出向量之间的距离,并通过相应的损失函数实现优化过程。结果表明使用基于余弦最大间隔距离损失函数的孪生网络获得了89.93%的准确率,优于实验中其它方法。此方法应用在发音偏误确认任务时,不使用标注的二语发音偏误数据训练的情况下,也获得了89.19%的诊断正确率。     

Combined neural network model employing wavelet coefficients for EEG signals classification

This paper illustrates the use of combined neural network model to guide model selection for classification of electroencephalogram (EEG) signals. The EEG signals were decomposed into time–frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first-level networks were implemented for the EEG signals classification using the statistical features as inputs. To improve diagnostic accuracy, the second-level networks were trained using the outputs of the first-level networks as input data. Three types of EEG signals (EEG signals recorded from healthy volunteers with eyes open, epilepsy patients in the epileptogenic zone during a seizure-free interval, and epilepsy patients during epileptic seizures) were classified with the accuracy of 94.83% by the combined neural network. The combined neural network model achieved accuracy rates which were higher than that of the stand-alone neural network model.     

Improving the accuracy and storage cost in biometric remote authentication schemes

Recently, Bringer et al. proposed a new approach for remote biometric based verification, which consists of a hybrid protocol that distributes the server side functionality in order to detach the biometric data storage from the service provider. Besides, a new security model is defined using the notions of Identity and Transaction Privacy, which guarantee the privacy of the identity-biometrics relationship under the assumption of non-colluding servers. However, due to the high communication and computational costs, the systems following this model cannot be implemented for large scale biometric systems.In this paper, we describe an efficient multi-factor biometric verification system with improved accuracy and lower complexity by considering the range information of every component of the user biometrics separately. Also, the new scheme is provably secure based on the security model of Bringer et al and implements a different database storage that eliminates the disadvantages of encrypted biometric templates in terms of ciphertext expansion. Also, we evaluate different Private Information Retrieval (PIR) schemes applicable for this setting and propose a practical solution for our scheme that reduces the computation costs dramatically. Finally, we compare our results with existing provably secure schemes and achieve reduced computational cost and database storage cost due to the single storage of the common features of the users in the system and amortization of the time complexity of the PIR.     

A non-intrusive biometric authentication mechanism utilising physiological characteristics of the human head

This paper proposes and evaluates a non-intrusive biometric authentication technique drawn from the discrete areas of biometrics and Auditory Evoked Responses. The technique forms a hybrid multi-modal biometric in which variations in the human voice due to the propagation effects of acoustic waves within the human head are used to verify the identity of a user. The resulting approach is known as the Head Authentication Technique (HAT). Evaluation of the HAT authentication process is realised in two stages. First, the generic authentication procedures of registration and verification are automated within a prototype implementation. Second, a HAT demonstrator is used to evaluate the authentication process through a series of experimental trials involving a representative user community. The results from the trials confirm that multiple HAT samples from the same user exhibit a high degree of correlation, yet samples between users exhibit a high degree of discrepancy. Statistical analysis of the prototype performance realised system error rates of 6% False Non-Match Rate (FNMR) and 0.025% False Match Rate (FMR).     

融合LeNet-5和Siamese神经网络模型的人脸认证算法研究

基于人脸信息的身份认证对于个人安全和社会稳定都具有非常重要的意义。传统的人脸认证方法依赖人工构造视觉特征,易受外界条件影响,识别精度不高。深度学习模型以自主学习方式进行特征提取,能从复杂的数据中提取到人脸的隐性特征。然而大部分深度学习人脸认证方法需大量带有身份标记的训练样本,额外增加了标记数据的成本。针对以上问题,提出了融合LeNet-5和Siamese神经网络模型的人脸认证算法。该算法在Siamese神经网络框架基础上,引入LeNet-5卷积神经网络,将单分支LeNet-5卷积网络扩充为结构相同且参数共享的双分支LeNet-5卷积网络,通过缩小卷积核、增加卷积层来调整网络结构,使用Contrastive Loss函数对融合网络进行训练。实验结果表明,该算法在不同的人脸数据集上,均获取较高的识别精度。     

Based blockchain-PSO-AES techniques in finger vein biometrics: A novel verification secure framework for patient authentication

The main objective of this study is to propose a novel verification secure framework for patient authentication between an access point (patient enrolment device) and a node database. For this purpose, two stages are used. Firstly, we propose a new hybrid biometric pattern model based on a merge algorithm to combine radio frequency identification and finger vein (FV) biometric features to increase the randomisation and security levels in pattern structure. Secondly, we developed a combination of encryption, blockchain and steganography techniques for the hybrid pattern model. When sending the pattern from an enrolment device (access point) to the node database, this process ensures that the FV biometric verification system remains secure during authentication by meeting the information security standard requirements of confidentiality, integrity and availability. Blockchain is used to achieve data integrity and availability. Particle swarm optimisation steganography and advanced encryption standard techniques are used for confidentiality in a transmission channel. Then, we discussed how the proposed framework can be implemented on a decentralised network architecture, including access point and various databases node without a central point. The proposed framework was evaluated by 106 samples chosen from a dataset that comprises 6000 samples of FV images. Results showed that (1) high-resistance verification framework is protected against spoofing and brute-force attacks; most biometric verification systems are vulnerable to such attacks. (2) The proposed framework had an advantage over the benchmark with a percentage of 55.56% in securing biometric templates during data transmission between the enrolment device and the node database.     

Secure biometric template generation for multi-factor authentication

In the light of recent security incidents, leading to compromise of services using single factor authentication mechanisms, industry and academia researchers are actively investigating novel multi-factor authentication schemes. Moreover, exposure of unprotected authentication data is a high risk threat for organizations with online presence. The challenge is how to ensure security of multi-factor authentication data without deteriorating the performance of an identity verification system? To solve this problem, we present a novel framework that applies random projections to biometric data (inherence factor), using secure keys derived from passwords (knowledge factor), to generate inherently secure, efficient and revocable/renewable biometric templates for users? verification. We evaluate the security strength of the framework against possible attacks by adversaries. We also undertake a case study of deploying the proposed framework in a two-factor authentication setup that uses users? passwords and dynamic handwritten signatures. Our system preserves the important biometric information even when the user specific password is compromised – a highly desirable feature but not existent in the state-of-the-art transformation techniques. We have evaluated the performance of the framework on three publicly available signature datasets. The results prove that the proposed framework does not undermine the discriminating features of genuine and forged signatures and the verification performance is comparable to that of the state-of-the-art benchmark results.     

基于因子分析模型的噪声稳健脑电信号分类方法

脑电信号的非线性、非平稳性和微弱性造成对运动想象脑电信号的分类存在特征提取困难,分类结果不理想,分类性能受噪声影响明显等问题。为此,提出了一种基于因子分析(Factor Analysis,FA)模型的噪声稳健运动脑电信号分类方法。首先利用FA模型对脑电信号中存在的噪声分量进行抑制,针对重构信号可分性较差的问题,将其转换至功率谱域,进而提取三维能够反映不同运动状态的功率谱特征,最后利用支撑向量机(Support Vector Machine,SVM)分类器对所提特征向量进行分类判决。基于Graz数据的验证实验表明,所提方法可以明显提升低信噪比条件下的分类性能,在实际工程应用中具备较强的推广泛化能力。     

基于混合神经网络的脑电时空特征情感分类

提出一种脑电图（electroencephalograph,简称EEG）数据表示方法,将一维链式EEG向量序列转换成二维网状矩阵序列,使矩阵结构与EEG电极位置的脑区分布相对应,以此来更好地表示物理上多个相邻电极EEG信号之间的空间相关性.再应用滑动窗将二维矩阵序列分成一个个等长的时间片段,作为新的融合了EEG时空相关性的数据表示.还提出了级联卷积-循环神经网络（CASC_CNN_LSTM）与级联卷积-卷积神经网络（CASC_CNN_CNN）这两种混合深度学习模型,二者都通过CNN卷积神经网络从转换的二维网状EEG数据表示中捕获物理上相邻脑电信号之间的空间相关性,而前者通过LSTM循环神经网络学习EEG数据流在时序上的依赖关系,后者则通过CNN卷积神经网络挖掘局部时间与空间更深层的相关判别性特征,从而精确识别脑电信号中包含的情感类别.在大规模脑电数据集DEAP上进行被试内效价维度上两类情感分类实验,结果显示,所提出的CASC_CNN_LSTM和CASC_CNN_CNN网络在二维网状EEG时空特征上的平均分类准确率分别达到93.15%和92.37%,均高于基准模型和现有最新方法的性能,表明该模型有效提高了EEG情感识别的准确率和鲁棒性,可以有效地应用到基于EEG的情感分类与识别相关应用中.     

Silog: Speech input logon

Silog is a biometric authentication system that extends the conventional PC logon process using voice verification. Users enter their ID and password using a conventional Windows logon procedure but then the biometric authentication stage makes a voice over IP (VoIP) call to a VoiceXML (VXML) server. User interaction with this speech-enabled component then allows the user’s voice characteristics to be extracted as part of a simple user/system spoken dialogue. If the captured voice characteristics match those of a previously registered voice profile, then network access is granted. If no match is possible, then a potential unauthorised system access has been detected and the logon process is aborted.     

A multimodal biometric watermarking system for digital images in redundant discrete wavelet transform

The traditional watermarking algorithms prove the rightful ownership via embedding of independent watermarks like copyright logos, random noise sequences, text etc into the cover images. Coupling biometrics with watermarking evolved as new and secure approach as it embeds user specific biometric traits and thus, narrows down the vulnerability to impostor attacks. A multimodal biometric watermarking system has been proposed in this paper in the redundant discrete wavelet transform(RDWT). Two biometric traits of the user i.e. the iris and facial features are embedded independently into the sub-bands of the RDWT of cover image taking advantage of its translation invariant property and sufficient embedding capacity. The ownership verification accuracy of the proposed system is tested based on the individual biometric traits as well as the fused trait. The accuracy was enhanced while using the fused score for evaluation. The security of the scheme is strengthened with usage of non-linear chaotic maps, randomization via Hessenberg decomposition, Arnold scrambling and multiple secret keys. The robustness of the scheme has been tested against various attacks and the verification accuracy evaluated based on false acceptance rate, false rejection rate, area under curve and equal error rate to validate the efficacy of the proposed scheme.

     

基于脑网络和TSK模糊系统的癫痫脑电识别

脑电检测是癫痫疾病诊断的重要手段,但基于脑电信号特征的人工标记方法,对癫痫发作状态识别的准确度较低。将脑功能网络与TSK模糊系统相结合,提出一种癫痫脑电信号识别的新方法。通过分析多通道脑电信号之间的同步性,构建癫痫患者的脑功能网络,采用复杂网络方法提取特征参数;以脑网络参数为输入特征建立TSK模糊系统模型,通过监督式学习训练分类器,用于识别癫痫发作期的脑电波形。实验结果证明了该方法的有效性,模糊分类器对癫痫发作状态识别的准确度达到98.36%,99.48%敏感度和97.24%特异度。该方法将复杂网络与机器学习算法相融合,为通过脑电检测识别癫痫疾病状态提供了新方法,具有重要的应用价值。     

A Channel Coding Approach for Human Authentication From Gait Sequences

Human authentication using biometric traits has become an increasingly important issue in a large range of applications. In this paper, a novel channel coding approach for biometric authentication based on distributed source coding principles is proposed. Biometric recognition is formulated as a channel coding problem with noisy side information at the decoder and error correcting codes are employed for user verification. It is shown that the effective exploitation of the noise channel distribution in the decoding process improves performance. Moreover, the proposed method increases the security of the stored biometric templates. As a case study, the proposed framework is employed for the development of a novel gait recognition system based on the extraction of depth data from human silhouettes and a set of discriminative features. Specifically, gait sequences are represented using the radial and the circular integration transforms and features based on weighted Krawtchouk moments. Analytical models are derived for the effective modeling of the correlation channel statistics based on these features and integrated in the soft decoding process of the channel decoder. The experimental results demonstrate the validity of the proposed method over state-of-the-art techniques for gait recognition.      

A novel framework for automatic 3D face recognition using quality assessment

The quality of biometric samples plays an important role in biometric authentication systems because it has a direct impact on verification or identification performance. In this paper, we present a novel 3D face recognition system which performs quality assessment on input images prior to recognition. More specifically, a reject option is provided to allow the system operator to eliminate the incoming images of poor quality, e.g. failure acquisition of 3D image, exaggerated facial expressions, etc.. Furthermore, an automated approach for preprocessing is presented to reduce the number of failure cases in that stage. The experimental results show that the 3D face recognition performance is significantly improved by taking the quality of 3D facial images into account. The proposed system achieves the verification rate of 97.09% at the False Acceptance Rate (FAR) of 0.1% on the FRGC v2.0 data set.     

NeuroBiometric: An Eye Blink Based Biometric Authentication System Using an Event-Based Neuromorphic Vision Sensor

The rise of the Internet and identity authentication systems has brought convenience to people's lives but has also introduced the potential risk of privacy leaks.Existing biometric authentication systems based on explicit and static features bear the risk of being attacked by mimicked data.This work proposes a highly efficient biometric authentication system based on transient eye blink signals that are precisely captured by a neuromorphic vision sensor with microsecond-level temporal resolution.The neuromorphic vision sensor only transmits the local pixel-level changes induced by the eye blinks when they occur,which leads to advantageous characteristics such as an ultra-low latency response.We first propose a set of effective biometric features describing the motion,speed,energy and frequency signal of eye blinks based on the microsecond temporal resolution of event densities.We then train the ensemble model and non-ensemble model with our Neuro Biometric dataset for biometrics authentication.The experiments show that our system is able to identify and verify the subjects with the ensemble model at an accuracy of 0.948 and with the non-ensemble model at an accuracy of 0.925.The low false positive rates(about 0.002)and the highly dynamic features are not only hard to reproduce but also avoid recording visible characteristics of a user's appearance.The proposed system sheds light on a new path towards safer authentication using neuromorphic vision sensors.     

基于遗传算法和灰色关联分析的击键特征识别算法

基于用户击键特征的身份认证比传统的基于口令的身份认证方法有更高的安全性，现有研究方法中基于神经网络、数据挖掘等算法计算复杂度高，而基于特征向量、贝叶斯统计模型等算法识别精度较低。为了在提高识别精度的同时有效降低计算复杂度，在研究现有算法的基础上提出了一种基于遗传算法与灰色关联分析的击键特征识别算法。该算法利用遗传算法根据用户训练样本确定表征用户击键特征的标准特征序列，通过对当前用户击键特征序列与标准特征序列进行灰色关联分析实现用户身份认证。实验结果表明，该算法识别精度达到神经网络、支持向量机等算法的较高水平，错误拒绝率与错误接受率分别为0%与1.5%。且计算复杂度低，与基于特征向量的算法相近。     

Fusion of physiological measures for multimodal biometric systems

Physiological measures are widely studied from a medical point of view. Most applications lie in the field of diagnosis of heart attacks, as regards the ECG, or the detection of epileptic events, in the case of the EEG. In the last ten years, these signals are being investigated also from a biometric point of view, in order to exploit the discriminative capability provided by these measures in recognizing individuals. The present work proposes a multimodal biometric recognition system based on the fusion of the first lead (i) of the electrocardiogram (ECG) with six different bands of the electroencephalogram (EEG). The proposed approach is based on the extraction of fiducial features (peaks) from the ECG combined with spectrum features of the EEG. A dataset has been created, by composing the signals of two well-known databases. The results, reported by means of EER values, AUC values and ROC curves, show good recognition performances.