Search

The vulnerability of deep networks towards adversarial perturbations has motivated the researchers to design detection and mitigation algorithms. Inspired by the dropout and dropconnect algorithms as well as augmentation techniques, this paper presents “PixelMask” based data augmentation as an efficient method of reducing the sensitivity of convolutional neural networks (CNNs) towards adversarial attacks. In the proposed approach, samples generated using PixelMask are used as augmented data, which helps in learning robust CNN models. Experiments performed with multiple databases and architectures show that the proposed PixelMask based data augmentation approach improves the classification performance on adversarially perturbed images. The proposed defense mechanism can be applied effectively for different adversarial attacks and can easily be combined with any deep neural network (DNN) architecture to increase the robustness. The effectiveness of the proposed defense is demonstrated in gray-box, white-box, and unseen train-test attack scenarios. For example, on the CIFAR-10 database under adaptive attack (i.e., projected gradient descent), the proposed PixelMask is able to improve the recognition performance of CNN by at-least 22.69%. Another advantage of the proposed algorithm over several existing defense algorithms is that the proposed defense either is able to retain or increase the classification accuracy of clean examples.

A reliable LULC model aims at predicting the spatial distribution of specific LULC classes for a later year by utilizing the trends from previous years thereby helps in appropriate LULC planning. The Ganga River Basin (GRB) has undergone significant LULC changes during past decades. The changes in LULC pattern was investigated for 1975 and 2010 to have better understanding of the conversion process and thereby predicting the future trend for 2045 using Dyna-CLUE (Conversion of Land-Use and its Effects) model. Four types of data were fed into the model i.e., (a) spatial policies and restrictions; (b) LULC type specific conversion settings; (c) LULC requirements (demands) and (d) location characteristics. The possible and impossible conversions among LULC classes were dealt with through Restriction and No Restriction area. The land conversion allocation was determined by establishing preference between LULC classes and the driving factors using binary logistic regression. Relative Operating Characteristic curves provided an overall value of 0.86 implying acceptability of regression results. The simulated result (with ‘no restriction’ area criteria) showed 578,296 km2 agriculture area in 2010 and 579,235 km2 for 2045, wherein 575,874 km2 (99.58%) of agriculture area could remain unchanged during 2010–2045; while with the restricted area, agriculture area of 577,675 km2 in 2010 and 578,516 km2 for 2045; whereas 576,242 km2 (99.75%) of agriculture area may remain unchanged during 2010–2045. Biophysical drivers namely altitude, slope, aspect, soil types, precipitation and temperature, emerged as major controlling factors for LULC change in GRB. Logistic regression analysis showed that population density is positively related with agriculture and expansion of settlements.

Deep learning models such as Convolutional Neural Networks (CNNs) have shown the potential to classify medical images for accurate diagnosis. These techniques will face regulatory compliance challenges related to privacy of user data, especially when they are deployed as a service on a cloud platform. Fully Homomorphic Encryption (FHE) can enable CNN inference on encrypted data and help mitigate such concerns. However, encrypted CNN inference faces the fundamental challenge of optimizing the computations to achieve an acceptable trade-off between accuracy and practical computational feasibility. Current approaches for encrypted CNN inference demonstrate feasibility typically on smaller images (e.g., MNIST and CIFAR-10 datasets) and shallow neural networks. This work is the first to show encrypted inference results on a real-world dataset for melanoma detection with large-sized images of skin lesions based on the Cheon-Kim-Kim-Song (CKKS) encryption scheme available in the open-source HElib library. The practical challenges related to encrypted inference are first analyzed and inference experiments are conducted on encrypted MNIST images to evaluate different optimization strategies and their role in determining the throughput and latency of the inference process. Using these insights, a modified LeNet-like architecture is designed and implemented to achieve the end goal of enabling encrypted inference on melanoma dataset. The results demonstrate that 80% classification accuracy can be achieved on encrypted skin lesion images (security of 106 bits) with a latency of 51 seconds for single image inference and a throughput of 18,000 images per hour for batched inference, which shows that privacy-preserving machine learning as a service (MLaaS) based on encrypted data is indeed practically feasible.

Research in face recognition has seen tremendous growth over the past couple of decades. Beginning from algorithms capable of performing recognition in constrained environments, the current face recognition systems achieve very high accuracies on large-scale unconstrained face datasets. While upcoming algorithms continue to achieve improved performance, a majority of the face recognition systems are susceptible to failure under disguise variations, one of the most challenging covariate of face recognition. Most of the existing disguise datasets contain images with limited variations, often captured in controlled settings. This does not simulate a real world scenario, where both intentional and unintentional unconstrained disguises are encountered by a face recognition system. In this paper, a novel Disguised Faces in the Wild (DFW) dataset is proposed which contains over 11000 images of 1000 identities with different types of disguise accessories. The dataset is collected from the Internet, resulting in unconstrained face images similar to real world settings. This is the first-of-a-kind dataset with the availability of impersonator and genuine obfuscated face images for each subject. The proposed dataset has been analyzed in terms of three levels of difficulty: (i) easy, (ii) medium, and (iii) hard in order to showcase the challenging nature of the problem. It is our view that the research community can greatly benefit from the DFW dataset in terms of developing algorithms robust to such adversaries. The proposed dataset was released as part of the First International Workshop and Competition on Disguised Faces in the Wild at CVPR, 2018. This paper presents the DFW dataset in detail, including the evaluation protocols, baseline results, performance analysis of the submissions received as part of the competition, and three levels of difficulties of the DFW challenge dataset.

Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities. In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks, (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem. Our experimental evaluation using multiple open-source DNN-based face recognition networks, and three publicly available face databases demonstrates that the performance of deep learning based face recognition algorithms can suffer greatly in the presence of such distortions. We also evaluate the proposed approaches on four existing quasi-imperceptible distortions: DeepFool, Universal adversarial perturbations, $$l_2$$ , and Elastic-Net (EAD). The proposed method is able to detect both types of attacks with very high accuracy by suitably designing a classifier using the response of the hidden layers in the network. Finally, we present effective countermeasures to mitigate the impact of adversarial attacks and improve the overall robustness of DNN-based face recognition.

Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms to adversarial attacks. Existing adversary detection algorithms attempt to detect the singularities; however, they are in general, loss-function, database, or model dependent. To mitigate this limitation, we propose DAMAD--a generalized perturbation detection algorithm which is agnostic to model architecture, training data set, and loss function used during training. The proposed adversarial perturbation detection algorithm is based on the fusion of autoencoder embedding and statistical texture features extracted from convolutional neural networks. The performance of DAMAD is evaluated on the challenging scenarios of cross-database, cross-attack, and cross-architecture training and testing along with traditional evaluation of testing on the same database with known attack and model. Comparison with state-of-the-art perturbation detection algorithms showcase the effectiveness of the proposed algorithm on six databases: ImageNet, CIFAR-10, Multi-PIE, MEDS, point and shoot challenge (PaSC), and MNIST. Performance evaluation with nearly a quarter of a million adversarial and original images and comparison with recent algorithms show the effectiveness of the proposed algorithm.

Blockchain has emerged as a leading technology that ensures security in a distributed framework. Recently, it has been shown that blockchain can be used to convert traditional blocks of any deep learning models into secure systems. In this research, we model a trained biometric recognition system in an architecture which leverages the blockchain technology to provide fault tolerant access in a distributed environment. The advantage of the proposed approach is that tampering in one particular component alerts the whole system and helps in easy identification of `any' possible alteration. Experimentally, with different biometric modalities, we have shown that the proposed approach provides security to both deep learning model and the biometric template., Published in IEEE BTAS 2019

In many areas in machine learning, decision trees play a crucial role in classification and regression. When a decision tree based classifier is hosted as a service in a critical application with the need for privacy protection of the service as well as the user data, fully homomorphic encrypted can be employed. However, a decision node in a decision tree can’t be directly implemented in FHE. In this paper, we describe an end-to-end approach to support privacyenhanced decision tree classification using IBM supported open-source library HELib. Using several options for building a decision node and employing oblivious computations coupled with an argmax function in FHE we show that a highly secure and trusted decision tree service can be enabled.

Several successful adversarial attacks have demonstrated the vulnerabilities of deep learning algorithms. These attacks are detrimental in building deep learning based dependable AI applications. Therefore, it is imperative to build a defense mechanism to protect the integrity of deep learning models. In this paper, we present a novel "defense layer" in a network which aims to block the generation of adversarial noise and prevents an adversarial attack in black-box and gray-box settings. The parameter-free defense layer, when applied to any convolutional network, helps in achieving protection against attacks such as FGSM, L 2 , Elastic-Net, and DeepFool. Experiments are performed with different CNN architectures, including VGG, ResNet, and DenseNet, on three databases, namely, MNIST, CIFAR-10, and PaSC. The results showcase the efficacy of the proposed defense layer without adding any computational overhead. For example, on the CIFAR-10 database, while the attack can reduce the accuracy of the ResNet-50 model to as low as 6.3%, the proposed "defense layer" retains the original accuracy of 81.32%.

Several computer vision applications such as object detection and face recognition have started to completely rely on deep learning based architectures. These architectures, when paired with appropriate loss functions and optimizers, produce state-of-the-art results in a myriad of problems. On the other hand, with the advent of "blockchain", the cybersecurity industry has developed a new sense of trust which was earlier missing from both the technical and commercial perspectives. Employment of cryptographic hash as well as symmetric/asymmetric encryption and decryption algorithms ensure security without any human intervention (i.e., centralized authority). In this research, we present the synergy between the best of both these worlds. We first propose a model which uses the learned parameters of a typical deep neural network and is secured from external adversaries by cryptography and blockchain technology. As the second contribution of the proposed research, a new parameter tampering attack is proposed to properly justify the role of blockchain in machine learning.

Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. Accuracy on dark-skinned females is significantly worse than on any other group. We provide initial evidence that skin type alone is not the driver for this disparity by conducting novel stability experiments that vary an image's skin type via color-theoretic methods, namely luminance mode-shift and optimal transport. We evaluate the effect of skin type change on the gender classification decision of a pair of state-of-the-art commercial and open-source gender classifiers. The results raise the possibility that broader differences in ethnicity, as opposed to the skin type alone, are what contribute to unequal gender classification accuracy in face images.

While deep learning is a valuable tool for solving many tough problems in computer vision, the success of deep learning models is typically determined by: (i) availability of sufficient training data, (ii) access to extensive computational resources, and (iii) expertise in selecting the right model and hyperparameters for the selected task. Often, the availability of data is the hard part due to compliance, legal, and privacy constraints. Cryptographic techniques such as fully homomorphic encryption (FHE) offer a potential solution by enabling processing on encrypted data. While prior work has been done on using FHE for inferencing, training a deep neural network in the encrypted domain is an extremely challenging task due to the computational complexity of the operations involved. In this paper, we evaluate the feasibility of training neural networks on encrypted data in a completely non-interactive way. Our proposed system uses the open-source FHE toolkit HElib to implement a Stochastic Gradient Descent (SGD)-based training of a neural network. We show that encrypted training can be made more computationally efficient by (i) simplifying the network with minimal degradation of accuracy, (ii) choosing appropriate data representation and resolution, and (iii) packing the data elements within the ciphertext in a smart way so as to minimize the number of operations and facilitate parallelization of FHE computations. Based on the above optimizations, we demonstrate that it is possible to achieve more than 50x speed up while training a fully-connected neural network on the MNIST dataset while achieving reasonable accuracy (96%). Though the cost of training a complex deep learning model from scratch on encrypted data is still very high, this work establishes a solid baseline and paves the way for relatively simpler tasks such as fine-tuning of deep learning models based on encrypted data to be implemented in the near future.

Mobile biometric approaches provide the convenience of secure authentication with an omnipresent technology. However, this brings an additional challenge of recognizing biometric patterns in an unconstrained environment including variations in mobile camera sensors, illumination conditions, and capture distance. To address the heterogeneous challenge, this research presents a novel heterogeneity aware loss function within a deep learning framework. The effectiveness of the proposed loss function is evaluated for periocular biometrics using the CSIP, IMP and VISOB mobile periocular databases. The results show that the proposed algorithm yields state-of-the-art results in a heterogeneous environment and improves generalizability for cross-database experiments.

Background: Hemophilia-an X linked congenital bleeding disorder because of deficiency in the coagulation factor VIII (in hemophilia A) or factor IX (in hemophilia B). The deficiency is due to the result of mutations of the clotting factor genes. Acute and chronic pain is commonly seen pain with hemophilia patients. Assessing of the cause of pain is essential for proper management. The choice of appropriate pain-relieving measures is difficult and challenging, as there are many complex factors affecting pain perception. There may be differences in patient’s experiences and their response to pain; hence, an individualized approach to pain management is required. Aim and Objectives: The objectives of the study were (i) to assess the efficacy of Paracetamol and Tramadol in pain management among hemophilic patient and (ii) to assess the adverse drug monitoring of Paracetamol and Tramadol among hemophilic patient. Materials and Methods: This study was a hospital-based prospective and observational crossover study, conducted at Hassan institute of Medical Sciences, Hassan, A 800 bedded multispecialty tertiary care teaching hospital over a period of 6 months (March 2019-August 2019). A prospective, observational, and crossover study, conducted on diagnosed and confirmed cases of hemophilia total 18 patients, age ranging from 18 to 50 years and being treated with Paracetamol 500 mg TID for 5 days followed washout period of 7 days, then Tramadol 50 mg BID for 5 days. Pain assessment (Visual analog scale) is done before (baseline) and after 5 days of each drugs. The results were analyzed using descriptive statistics. Results: In our study, out of 18 male patients who are enrolled in the study from inpatient medicine department, patients belonged to age group of 18–50 years. Statistical Significant decrease in pain was seen with Tramadol compared to Paracetamol. Conclusion: Tramadol 50 mg BD is better than Paracetamol 500mg TID for pain management in hemophilia patients. As all patients would be suffering from deep seated pain, which is resolved by weak Opiod. Safer alternative for mild pain relief is Paracetamol (11%). Life expectancy and Quality of life will be improved with appropriate pain relief medication.

The mechanisms whereby immune therapies affect progression of type 1 diabetes (T1D) are not well understood. Teplizumab, an FcR nonbinding anti-CD3 mAb, has shown efficacy in multiple randomized clinical trials. We previously reported an increase in the frequency of circulating CD8(+) central memory (CD8CM) T cells in clinical responders, but the generalizability of this finding and the molecular effects of teplizumab on these T cells have not been evaluated. We analyzed data from two randomized clinical studies of teplizumab in patients with new- and recent-onset T1D. At the conclusion of therapy, clinical responders showed a significant reduction in circulating CD4(+) effector memory T cells. Afterward, there was an increase in the frequency and absolute number of CD8CM T cells. In vitro, teplizumab expanded CD8CM T cells by proliferation and conversion of non-CM T cells. Nanostring analysis of gene expression of CD8CM T cells from responders and nonresponders versus placebo-treated control subjects identified decreases in expression of genes associated with immune activation and increases in expression of genes associated with T-cell differentiation and regulation. We conclude that CD8CM T cells with decreased activation and regulatory gene expression are associated with clinical responses to teplizumab in patients with T1D.

Deep learning algorithms provide state-of-the-art results on a multitude of applications. However, it is also well established that they are highly vulnerable to adversarial perturbations. It is often believed that the solution to this vulnerability of deep learning systems must come from deep networks only. Contrary to this common understanding, in this article, we propose a non-deep learning approach that searches over a set of well-known image transforms such as Discrete Wavelet Transform and Discrete Sine Transform, and classifying the features with a support vector machine-based classifier. Existing deep networks-based defense have been proven ineffective against sophisticated adversaries, whereas image transformation-based solution makes a strong defense because of the non-differential nature, multiscale, and orientation filtering. The proposed approach, which combines the outputs of two transforms, efficiently generalizes across databases as well as different unseen attacks and combinations of both (i.e., cross-database and unseen noise generation CNN model). The proposed algorithm is evaluated on large scale databases, including object database (validation set of ImageNet) and face recognition (MBGC) database. The proposed detection algorithm yields at-least 84.2% and 80.1% detection accuracy under seen and unseen database test settings, respectively. Besides, we also show how the impact of the adversarial perturbation can be neutralized using a wavelet decomposition-based filtering method of denoising. The mitigation results with different perturbation methods on several image databases demonstrate the effectiveness of the proposed method.

Existing research in the field of face recognition with variations due to disguises focuses primarily on images captured in controlled settings. Limited research has been performed on images captured in unconstrained environments, primarily due to the lack of corresponding disguised face datasets. In order to overcome this limitation, this work presents a novel Disguised Faces in the Wild (DFW) dataset, consisting of over 11,000 images for understanding and pushing the current state-of-the-art for disguised face recognition. To the best of our knowledge, DFW is a first-of-a-kind dataset containing images pertaining to both obfuscation and impersonation for understanding the effect of disguise variations. A major portion of the dataset has been collected from the Internet, thereby encompassing a wide variety of disguise accessories and variations across other covariates. As part of CVPR2018, a competition and workshop are organized to facilitate research in this direction. This paper presents a description of the dataset, the baseline protocols and performance, along with the phase-I results of the competition.

Increased individual mobility has pushed the modern society needs for a reliable individual identity verification system as a critical component in many transactions in commercial industries, public sectors and government domains. The requirement for an ideal human identity verification is critical to security and prevention of identity fraud. Thus, trusted identity management has become an essential part of contemporary system infrastructure. It is now well accepted that biometrics-the science of identifying a person (or verifying their identity) based on their physiological or behavioral characteristics-can provide significant value when building such systems. Three key cornerstones in a trusted biometrics-based identity system include the following: (a) A trusted identity enrollment process (b) A trusted identity verification process (c) An identity credential management mechanism. In this chapter, we present several emerging developments in mobile biometrics technologies with particular focus on futuristic cognitive authentication systems for enabling large-scale trusted identity management systems based on biometrics and also biometrics identity services in the cloud. Biometrics is excellent mechanisms for the authentication or identification of individuals because of the credential's uniqueness and persistence almost over the lifetime of the person. Biometric identity services in the cloud enable mobile biometrics wide adoption economically and also take advantages of adjacent technology advancements.

Type 1 diabetes is an organ-specific autoimmune disease, characterized by selective destruction of insulin-producing pancreatic β-cells by T-cell-mediated inflammation. Beginning with studies of cyclosporin A in the 1980s, but with more activity in the past decade, there have been a number of clinical trials to test whether immunotherapies can arrest the decline in C-peptide, which is associated with progression of type 1 diabetes leading to the metabolic instability that characterizes the disease. One of the most promising agents, teplizumab , is an FcR-nonbinding anti-CD3 monoclonal antibody that has been tested in Phase II - III clinical trials and was shown to preserve the C-peptide levels and reduce the need for exogenous insulin.In this review, we discuss the recent update on clinical data obtained from trials of teplizumab in type 1 diabetes, the drug's postulated mechanism of action and the identification of responders to therapy. We highlight the results of recent trials as well as the lessons that have been learned from the clinical trials involving selection of end points and the inclusion of diverse study populations.Teplizumab has been shown to preserve β cell function in patients; however, it does not represent a 'cure' for patients, and its efficacy does entail a significant advance in arresting the progression of the disease toward complete insulin deficiency and reliance on exogenous insulin.

Cytomegalovirus (CMV) reactivation may lead to CMV disease associated with high morbidity and mortality in patients after hematopoietic stem cell transplantation (HSCT); the identification of clinically relevant markers may aid in the identification of patients at increased risk for developing CMV-associated complications. We evaluated the phosphorylation of signal transducer and activator of transcription 5 (STAT5) in CD4+ T cells, CD8+ T cells, and TCRγδ T cells in response to stimulation with IL-7 or IL-2 after HSCT by analyzing blood samples taken monthly 1 to 6 months after HSCT. Patients were monitored weekly with a quantitative PCR from the time of engraftment for CMV viral load in whole blood until at least day 100 after HSCT. We identified a correlation between clinical outcome regarding CMV replication and the ability to respond to IL-7 and IL-2 defined by STAT5 phosphorylation (pSTAT5). Patients with recurrent or prolonged CMV replications had significantly lower pSTAT5 upon stimulation of T cells with either IL-7 or IL-2 at time points 1 through 3 than those without CMV replication (P < .05). This was also found after stimulation of CD8+ T cells at time point 2 (P < .05). We conclude that reduced responses to IL-7, reflected by pSTAT5, may represent a clinically relevant functional biomarker for individuals at increased risk for CMV reactivation; our data may also aid in designing better strategies to improve anti-CMV immune responses without increasing the risk of developing graft-versus-host disease.

Classifier fusion is a well-studied problem in which decisions from multiple classifiers are combined at the score, rank, or decision level to obtain better results than a single classifier. Subsequently, various techniques for combining classifiers at each of these levels have been proposed in the literature. Many popular methods entail scaling and normalizing the scores obtained by each classifier to a common numerical range before combining the normalized scores using the sum rule or another classifier. In this research, we explore an alternative method to combine classifiers at the score level. The Pool Adjacent Violators (PAV) algorithm has traditionally been utilized to convert classifier match scores to confidence values that model posterior probabilities for test data. The PAV algorithm and other score normalization techniques have studied the same problem without being aware of each other. In this first ever study to combine the two, we propose the PAV algorithm for classifier fusion on publicly available NIST multi-modal biometrics score dataset. We observe that it provides several advantages over existing techniques and find that the interpretation learned by the PAV algorithm is more robust than the scaling learned by other popular normalization algorithms such as min-max. Moreover, the PAV algorithm enables the combined score to be interpreted as confidence and is able to further improve the results obtained by other approaches. We also observe that utilizing traditional normalization techniques first for individual classifiers and then normalizing the fused score using PAV offers a performance boost compared to only using the PAV algorithm.

Biometric systems can be attacked in several ways and the most common being spoofing the input sensor. Therefore, anti-spoofing is one of the most essential prerequisite against attacks on biometric systems. For face recognition it is even more vulnerable as the image capture is non-contact based. Several anti-spoofing methods have been proposed in the literature for both contact and non-contact based biometric modalities often using video to study the temporal characteristics of a real vs. spoofed biometric signal. This paper presents a novel multi-feature evidence aggregation method for face spoofing detection. The proposed method fuses evidence from features encoding of both texture and motion (liveness) properties in the face and also the surrounding scene regions. The feature extraction algorithms are based on a configuration of local binary pattern and motion estimation using histogram of oriented optical flow. Furthermore, the multi-feature windowed videolet aggregation of these orthogonal features coupled with support vector machine-based classification provides robustness to different attacks. We demonstrate the efficacy of the proposed approach by evaluating on three standard public databases: CASIA-FASD, 3DMAD and MSU-MFSD with equal error rate of 3.14%, 0%, and 0%, respectively.

Often deep learning methods are associated with huge amounts of training data. The deeper the network gets, the larger is the need for training data. A large amount of labeled data helps the network learn about the variations it needs to handle in the prediction stage. It is not easy for everyone to get access to huge amounts of labeled data leaving a few to have the luxury to design very deep networks. In this paper, we propose to flatten the disparity by using the modeling methods to minimize the need for huge amounts of data for training a deep network. Using face recognition as an example, we demonstrate how limited labeled data can be leveraged to obtain near state of the art performance with generalization capability across multiple databases. In addition, we show that the normalization in the overall network can improve the speed and resource requirement for the prediction/inferencing stage.

A personal or enterprise collection of a large set of face images may contain many types of tags used for querying the collection. Often the tags have many irrelevant content that may not reflect the image content in terms of the facial characteristics. In this paper, we propose a data curation method to filter out the irrelevant face images using a face recognition based subgraph identification. Results on retrievals from the Internet using popular celebrities show the efficacy of our approach after we cleanse the images collection retrieved and applying our algorithm to the collection.

It has been shown that significant age difference between a probe and gallery face image can decrease the matching accuracy. If the face images can be normalized in age, there can be a huge impact on the face verification accuracy and thus many novel applications such as matching driver's license, passport and visa images with the real person's images can be effectively implemented. Face progression can address this issue by generating a face image for a specific age. Many researchers have attempted to address this problem focusing on predicting older faces from a younger face. In this paper, we propose a novel method for robust and automatic face progression in totally unconstrained conditions. Our method takes into account that faces belonging to the same age-groups share age patterns such as wrinkles while faces across different age-groups share some common patterns such as expressions and skin colors. Given training images of K different age-groups the proposed method learns to recover K low-rank age and one low-rank common components. These extracted components from the learning phase are used to progress an input face to younger as well as older ages in bidirectional fashion. Using standard datasets, we demonstrate that the proposed progression method outperforms state-of-the-art age progression methods and also improves matching accuracy in a face verification protocol that includes age progression.

The level of Epstein-Barr virus DNA in blood has proven to be a biomarker with some predictive value in allogeneic hematopoietic stem cell transplantation patients (HSCT). We evaluated the impact of EBV load on survival of 51 patients (32M/19F, median age: 32 years, from < 1 to 68 years old), who had received HSCT for different types of malignancies (49 cases) or non-malignancies (2 cases). The overall survival [1]was compared between patients with extreme and moderate cell bound EBV DNA levels. Different sources of stem-cells (peripheral blood stem, n = 39; bone marrow, n = 9; or umbilical cord blood, n = 3) were used. Twenty patients received reduced-intensity conditioning regimen while the other 31 received myeloablative conditioning. Patients with high or very low level of cell bound EBV-DNA levels had a shorter OS than those with moderate EBV load: OS at 5 years was 67% vs 90% (p < 0.03). There was a conspicuous relationship between EBV load and the reconstitution dynamics of total and EBV-specific T cells, CD4+ and CD4- CD8- (double negative) T cells in the few patients where it was analyzed. This was not statistically significant. Two other factors were associated to early mortality in addition to high or low EBV load: acute GVHD II-IV (p < 0.02) and pre-transplant conditioning with total body irradiation (TBI) ≥6 Gy, (p < 0.03). All the patients meeting all three criteria died within two years after transplantation. This points to a subgroup of HSCT patients which deserve special attention with improvement of future, personalized treatment.

Purpose: To examine the clinical and gonioscopic findings in patients with glaucoma associated with Sturge–Weber syndrome. Methods: Retrospective review of clinical findings of all patients with Sturge–Weber syndrome who presented between January 1978 and December 2003. Koeppe gonioscopy was performed under general anesthesia and findings were photographed when feasible. Iris color was documented by color sketch or photograph at initial presentation. Fisher exact test was used to determine whether the presence of heterochromia was statistically higher in the glaucomatous group. Results: Fifty-five patients who met inclusion criteria were identified, of whom 44 (80%) had glaucoma. Unilateral glaucoma was diagnosed in 30 eyes and bilateral glaucoma in 14 eyes, yielding 58 eyes with glaucoma and 52 eyes without. Gonioscopic examination revealed distinct anatomic abnormalities in the anterior chamber angle in 32 (55%) of the glaucomatous eyes in contrast to the normal fellow eyes in patients with unilateral glaucoma and to the patients without glaucoma. Heterochromia iridis with darker iris on the glaucomatous side was present in 11 of the 30 patients with unilateral glaucoma (37%, P < .001) but in none of the patients without glaucoma. Conclusion: The characteristics observed in the anterior chamber angle in this large, uniquely examined series are the first reported to the authors’ knowledge and may support a role for neural crest derived anomalies in the pathogenesis of glaucoma in these infant eyes. Careful examination for heterochromia iridis may be judicious in these patients.

Between January 2001 and June 2008, 315 adult patients (median age 43 years, range 16-65) including 203 males and 112 females undergoing hematopoietic stem cell transplantation (HSCT) had serial monitoring for cytomegalovirus (CMV) followed by initiation of preemptive therapy. The majority (62.1%) had a conventional myeloablative transplant with 116 (36.9%) having a reduced-intensity conditioning (RIC) transplant, using either matched sibling/family (63.3%) or unrelated donors (36.7%). Graft source was peripheral blood stem cells in 257 (81.5%), bone marrow in 41 (13.1%), and cord blood in 16 (5.4%). T-cell depletion with anti-thymocyte globulin or alemtuzumab was used in 35%. Based upon CMV serostatus, patients were classified into low risk (donor [D]-/recipient [R]-), intermediate risk (D+/R-), or high risk (D-/R+ or D+/R+). Serial weekly monitoring for CMV viremia was performed using a qualitative polymerase chain reaction (PCR) and when positive, quantification was done using either pp65 antigen or a quantitative PCR. CMV reactivation was seen in 123 patients (39.1%) at a median of 50 days post HSCT (range 22-1978). CMV serostatus was the most important risk factor with incidence of 53% in the high-risk group (53.3%) compared with 10.2% in the intermediate risk and 0% in the low-risk group (P

Biometrics-based authentication systems offer obvious usability advantages over traditional password and token-based authentication schemes. However, biometrics raises several privacy concerns. A biometric is permanently associated with a user and cannot be changed. Hence, if a biometric identifier is compromised, it is lost forever and possibly for every application where the biometric is used. Moreover, if the same biometric is used in multiple applications, a user can potentially be tracked from one application to the next by cross-matching biometric databases. In this paper, we demonstrate several methods to generate multiple cancelable identifiers from fingerprint images to overcome these problems. In essence, a user can be given as many biometric identifiers as needed by issuing a new transformation "key." The identifiers can be cancelled and replaced when compromised. We empirically compare the performance of several algorithms such as Cartesian, polar, and surface folding transformations of the minutiae positions. It is demonstrated through multiple experiments that we can achieve revocability and prevent cross-matching of biometric databases. It is also shown that the transforms are noninvertible by demonstrating that it is computationally as hard to recover the original biometric identifier from a transformed version as by randomly guessing. Based on these empirical results and a theoretical analysis we conclude that feature-level cancelable biometric construction is practicable in large biometric deployments.

Interleukin-7-receptor-signaling plays a pivotal role in T-cell development and maintenance of T-cell memory. We studied IL-7Ralpha (CD127) expression in PBMCs obtained from patients with breast cancer and examined IL-7 receptor-mediated downstream effects defined by STAT5 phosphorylation (p-STAT5). Reduced numbers of IL-7Ralpha-positive cells were identified in CD4+ T-cells as well as in a CD8+ T-cell subset defined by CD8alpha/alpha homodimer expression in patients with breast cancer. PBMCs obtained from healthy donors (n = 19) and from patients with breast cancer (n = 19) exhibited constitutive p-STAT5 expression in the range of 0-6.4% in CD4+ T-cells and 0-4% in CD8+ T-cells. Stimulation with recombinant human IL-7 for 15 min increased p-STAT5 expression up to 36-97% in CD4+T-cells and to 26-90% in CD8+T-cells obtained from healthy control donors (n = 19). In contrast, PBMCs obtained from 13/19 patients with breast cancer did not respond to IL-7 as defined by STAT5 phosphorylation, despite expression of IL-7Ralpha on T-lymphocytes. T-cells were further characterized for IL- 2 and IFN-gamma production induced by PMA/Ionomycin. PBMCs from 9/19 patients with breast cancer showed decreased IL-2 and IFN-gamma production combined with IL-7-signaling defects; PBMCs from 4 patients with breast cancer exhibited deficient IL-7-signaling, yet intact cytokine production. Reduced numbers of IL-7Ralpha-positive cells and nonresponsiveness to IL-7, defined by lack of STAT5 phosphorylation, characterizes the immunological profile in T-cells from patients with breast cancer.

This article reports a case of progressive glaucomatous optic neuropathy and visual field loss that occurred in a patient who practiced the Sirsasana (headstand) yoga posture on a daily basis for many years. Visual field analysis was performed through standard automated perimetry. Intraocular pressure (IOP) was measured through pneumotonometry in the sitting position and in the head-down position. Stereo-optic disc photographs were obtained. IOP increased significantly in the head-down position. Optic disc evaluation revealed a new disc hemorrhage in the left eye. Visual field analysis over a period of 2 y showed progression of a superior arcuate defect in the left eye. Transient increases in IOP associated with the yoga headstand posture may lead to progressive glaucomatous optic nerve damage and visual field loss.

Objective: We compared profiles of the numbers of circulating endothelial cells (CEC) and the apoptosis-inducing capacity of serum samples on human endothelial cells (hEC) in on-pump and off-pump coronary artery bypass grafting (CABG) patients. Methods: Blood samples from 30 patients undergoing CABG (randomly assigned to two groups: 15 patients off-pump and 15 on-pump (cardiopulmonary bypass, CPB)) were collected after induction of anesthesia (preoperatively), at weaning from CPB/end of bypass grafting (0 h), and 1, 6, 12, 24, and 48 h afterwards. CEC were isolated with immunomagnetic anti-CD146-coated Dynabeads, and counted in a Nageotte chamber. The apoptosis-inducing activity of serum samples on hEC was examined by a tissue culture assay system. Apoptotic and normal cells were identified using phase contrast/ fluorescence microscopy after DNA dye staining. Results: CEC numbers and proportions of apoptotic hEC were significantly elevated during and after surgery in both groups (p < 0.01). Compared with the on-pump group, CEC and proportions of apoptotic hEC were significantly lower (p = 0.04 and p = 0.03, respectively) in patients having CABG performed off-pump. Starting at comparable baseline levels, the mean CEC-number was highest at 6 h postoperatively with 81.9 ml -1 (range, 44-141) for on-pump patients and 63.3 ml -1 (range, 48-105) for off-pump patients. hEC apoptosis peaked also at T4: 16.5 ± 2.8% versus 11.3 ± 2.2%. In both groups, CEC numbers and proportions of endothelial apoptosis were still elevated at 48 h after surgery. Conclusion: The number of circulating endothelial cells and apoptotic endothelial cell death are markers of endothelial activation and damage during CABG. This study provides evidence that CABG with the use of CPB in comparison to OPCAB surgery is associated with a significantly more pronounced endothelial response in the immediate postoperative period.

Face recognition algorithms are generally trained for matching high-resolution images and they perform well for similar resolution test data. However, the performance of such systems degrades when a low-resolution face image captured in unconstrained settings, such as videos from cameras in a surveillance scenario, are matched with high-resolution gallery images. The primary challenge, here, is to extract discriminating features from limited biometric content in low-resolution images and match it to information rich high-resolution face images. The problem of cross-resolution face matching is further alleviated when there is limited labeled positive data for training face recognition algorithms. In this paper, the problem of cross-resolution face matching is addressed where low-resolution images are matched with high-resolution gallery. A co-transfer learning framework is proposed, which is a cross-pollination of transfer learning and co-training paradigms and is applied for cross-resolution face matching. The transfer learning component transfers the knowledge that is learnt while matching high-resolution face images during training to match low-resolution probe images with high-resolution gallery during testing. On the other hand, co-training component facilitates this transfer of knowledge by assigning pseudolabels to unlabeled probe instances in the target domain. Amalgamation of these two paradigms in the proposed ensemble framework enhances the performance of cross-resolution face recognition. Experiments on multiple face databases show the efficacy of the proposed algorithm and compare with some existing algorithms and a commercial system. In addition, several high profile real-world cases have been used to demonstrate the usefulness of the proposed approach in addressing the tough challenges.

Traditional fingerprint acquisition is limited to single-image capture and processing. With the advent of faster capture hardware, faster processors, and advances in video compression standards, newer systems can capture and exploit video signals for tasks that are difficult using a single image. We propose the use of fingerprint video sequences to investigate detecting two aspects of the dynamic behavior of fingerprints. Specifically, we are interested in the detection of distortion of fingerprint impressions due to excessive force and the detection of the positioning of fingers during image capture. These issues often lead to difficulties in establishing a precise match between acquired images. The proposed techniques investigate dynamic characteristics of fingerprints across video sequence frames. A significant advantage of our approach for distortion analysis is that it works directly on MPEG-1,-2 encoded fingerprint video bitstreams. The proposed methods have been tested on the NIST-24 live-scan fingerprint video database and the results are promising. We also describe a new concept called the "resultant biometrics", a new type of biometrics which has both a physiological, physical (e.g., force, torque, linear motion, rotation) component and/or a temporal characteristic, added by a subject to an existing biometric. This resultant biometric is both desirable and efficient in terms of easy modification of compromised biometrics and is harder to produce with spoof body parts.

A biometric system is an instance of a pattern recognition system with well-defined error conditions, which allows objective statistical error analysis. Biometrics is an emerging technology with fierce competition between many manufacturers using a variety of biometrics, such as, fingerprints, for recognizing human identities. Manufacturers of biometric systems are continuously refining the technology and claiming "high accuracy." This may be defined simply as a system that works or as a system that makes very few or no errors. Obviously, such loose definitions of accuracy are undesirable and there is a need for a precise definition. We argue that biometric match score accuracy is best expressed in terms of a curve, the Receiver Operating Characteristic curve. More importantly, we argue that confidence intervals, or margins of error, should be provided for this curve. This allows for determining whether accuracy differences between systems are really statistically significant. We introduce a novel bootstrap technique for computing the confidence regions of the error estimates and compare them to a commonly used parametric method. This bootstrap technique is inspired by the moving blocks bootstrap, which samples with replacement from blocks of data thereby accounting for dependence among the data. Our approach samples with replacement from specifically determined subsets of the data. We call this new bootstrap technique "the subsets bootstrap."

Currently there is much interest in the use of biometrics for authentication and identification applications. This has been heightened most recently because of the threat of terrorism. Biometrics authentication and identification systems offer several advantages over systems based on knowledge or possession such as unsupervised (legacy) password/PIN-based systems and supervised (legacy) passport-based systems. To optimize security it is important that biometrics authentication systems are designed to withstand different sources of attack. We identify some such threats to biometrics systems and detail issues related to the tradeoff between security and convenience. We further show how to estimate a biometrics' intrinsic security, sometimes called a biometrics' individuality, with fingerprints as an example.

Biometrics authentication offers many advantages over conventional authentication systems that rely on possessions or special knowledge. With conventional technology, often the mere possession of an employee ID card is proof of ID, while a password potentially can be used by large groups of colleagues for long times without change. The fact that biometrics authentication is non-repudiable (hard to refute) and, yet, convenient, is among its most important advantages. Biometrics systems, however, suffer from some inherent biometrics-specific security threats. These threats are mainly related to the use of digital signals and the need for additional input devices, though we also discuss brute-force attacks of biometrics systems. There are also problems common to any pattern recognition system. These include “wolves” and “lambs”, and a new group we call “chameleons”. An additional issue with the use of biometrics is the invasion of privacy because the user has to enroll with an image of a body part. We discuss these issues and suggest some methods for mitigating their impact.

Background Interleukin 7 (IL-7) signals via the IL-7 receptor (IL-7R) and drives homeostatic T-cell proliferation in patients after allogeneic hematopoietic stem cell transplantation (aHSCT). Purpose We performed a prospective study in adults (n = 33) and children (n = 29) undergoing aHSCT measuring plasma IL-7 and soluble IL-7R (sIL-7R) concentrations between 1 and 12 months after HSCT in order to investigate the link between sIL-7R and clinical events after aHSCT. Results sIL-7R, but not IL-7, increased with time after HSCT in plasma from all patients enrolled in the study. sIL-7R values were higher at 2, 3, and 6 months (p 0.01) and sibling donors (RH: 2.23, p = 0.004). Recipients of sibling grafts showed high levels of IL-7 (RH: 1.38, p

Background Herpes simplex virus type 2 (HSV-2; herpes) exacerbates human immunodeficiency virus type 1 (HIV) by unclear mechanisms. These studies tested the impact of HSV-2 on systemic T-cells and HIV reservoirs. Methods Peripheral blood mononuclear cells from HIV-infected women on antiretroviral therapy who were HSV-2 seropositive or seronegative and HIV-uninfected controls were analyzed by flow cytometry. Cell-associated HIV DNA and RNA were quantified in the absence or presence of activating stimuli, recombinant interleukin 32γ (IL-32γ), and a RUNX1 inhibitor. RNA was assessed by nanostring. Results CD4, but not CD8, T-cell phenotypes differed in HIV+/HSV-2+ versus HIV+/HSV-2- (overall P = .002) with increased frequency of CCR5+, CXCR4+, PD-1+, and CD69+ and decreased frequency of CCR10+ and CCR6+ T-cells. The changes were associated with higher HIV DNA. Paradoxically, IL-32, a proinflammatory cytokine, was lower in subpopulations of CD4+ T-cells in HSV-2+ versus HSV-2- women. Recombinant IL-32γ blocked HIV reactivation in CD4+ T-cells and was associated with an increase in RUNX1 expression; the blockade was overcome by a RUNX1 inhibitor. Conclusions Herpes is associated with phenotypic changes in CD4+ T-cells, including a decrease in IL-32, which may contribute to increased HIV reservoirs. Blocking IL-32 may facilitate HIV reactivation to improve shock and kill strategies.

Because biometrics-based authentication offers several advantages over other authentication methods, there has been a significant surge in the use of biometrics for user authentication in recent years. It is important that such biometrics-based authentication systems be designed to withstand attacks when employed in security-critical applications, especially in unattended remote applications such as e-commerce. In this paper we outline the inherent strengths of biometrics-based authentication, identify the weak links in systems employing biometrics-based authentication, and present new solutions for eliminating some of these weak links. Although, for illustration purposes, fingerprint authentication is used throughout, our analysis extends to other biometrics-based methods.

The engineered Fc-nonbinding (crystallizable fragment-nonbinding) CD3 antibody has lower mitogenicity and a precise therapeutic window for disease remission in patients with type 1 diabetes. Before anti-CD3 can be considered for use in transplantation, the most effective timing of treatment relative to transplantation needs to be elucidated. In this study anti-CD3F(ab′)2 fragments or saline were administered intravenously for 5 consecutive days (early: d1–3 or delayed: d3–7) to mice transplanted with a cardiac allograft (H2b-to-H2k; d0). Survival of allografts was prolonged in mice treated with the early protocol (MST = 48 days), but most were rejected by d100. In contrast, in mice treated with the delayed protocol allografts continued to survive long term. The delayed protocol significantly inhibited donor alloreactivity at d30 as compared to the early protocol. A marked increase in Foxp3+ T cells (50.3 ± 1.6%) infiltrating the allografts in mice treated with the delayed protocol was observed (p < 0.0001 vs. early (24.9 ± 2.1%)) at d10; a finding that was maintained in the accepted cardiac allografts at d100. We conclude that the timing of treatment with anti-CD3 therapy is critical for inducing long-term graft survival. Delaying administration effectively inhibits the alloreactivity and promotes the dominance of intragraft Foxp3+ T cells allowing long-term graft acceptance.

This paper pertains to the detection of objects located in complex backgrounds. A feature-based segmentation approach to the object detection problem is pursued, where the features are computed over multiple spatial orientations and frequencies. The method proceeds as follows: a given image is passed through a bank of even-symmetric Gabor filters. A selection of these filtered images is made and each (selected) filtered image is subjected to a nonlinear (sigmoidal like) transformation. Then, a measure of texture energy is computed in a window around each transformed image pixel. The texture energy (“Gabor features”) and their spatial locations are inputted to a squared-error clustering algorithm. This clustering algorithm yields a segmentation of the original image—it assigns to each pixel in the image a cluster label that identifies the amount of mean local energy the pixel possesses across different spatial orientations and frequencies. The method is applied to a number of visual and infrared images, each one of which contains one or more objects. The region corresponding to the object is usually segmented correctly, and a unique signature of “Gabor features” is typically associated with the segment containing the object(s) of interest. Experimental results are provided to illustrate the usefulness of this object detection method in a number of problem domains. These problems arise in IVHS, military reconnaissance, fingerprint analysis, and image database query.

Biologically inspired model (BIM) is proven to be an effective feature representation approach for visual object categorization. In BIM, two successive S(simple)-to-C(complex) hierarchical layers are performed to simulate the visual perception process of primate visual cortex. However, the intensive computational cost above C1 layer in BIM extremely limits its application in real-time object recognition tasks. This paper proposes to use a set of improved early biologically inspired features (EBIF, including S1 and C1) for face recognition, in which pyramidal statistics of mean and standard deviation rather than MAX pooling are used for scale-tolerant feature condensation and local normalization is performed on C1 layer. Incremental PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) are then combined to efficiently learn a discriminant subspace for feature dimensionality reduction. In the matching stage, Cosine similarity is adopted as the distance metric for a given face pair. Experimental results on two public face datasets and a mobile face dataset show the effectiveness of the proposed method.

Iris recognition has gained popularity due to factors such as its perceived high accuracy, significant usability advantages attributed to its non-contact acquisition method, and the availability of low cost sensors due to improvements in technology. However, non-contact biometrics authentication systems are vulnerable to different types of attacks than contact-type biometrics, such as fingerprints, for which there are a number of simple techniques to guard against attacks. In particular, the fashion industry has developed designer contact lenses with patterns that range from a simple change in eye color to the imposition of stars or other festive decorations. As these lenses are readily available and can be personalized at a very affordable price, their use in thwarting or spoofing iris-based authentication systems becomes plausible. Given the high security nature of many of these systems, there is a urgent need for a some countermeasure to this type of attack. In this paper, we describe a novel method to detect the presence of fake iris patterns, such as designer contact lenses, during the image acquisition stage to further enhance the basic security value of iris biometrics. Exploiting the anatomy and geometry of the human eye, we present a structured light projection method to detect the presence of artificial items obscuring the real iris. The detection principle has been verified using an inexpensive experimental setup consisting of a miniature projector and an offset camera. We also describe a novel algorithm to process the acquired images to find patterned contact lenses, and measure its performance using data collected with our apparatus. We argue that the addition of the proposed system and algorithm to existing iris biometrics based authentication systems will significantly improve their security.

Background: Calcium sulfate belongs to synthetic ceramic group of bone graft substitutes having an osteoconductive property. Calcium sulfate is an easily available, economic bone graft substitute. It is a bio-inert material which over a period of weeks get resorbed and fibrovascular tissue takes its place which eventually allows neovascularisation and bone formation within the area. Use of calcium sulfate as a bone graft substitutes avoids the complications and morbidity associated with autograft like infection, second surgery, and finite amount of graft. Material and Methods: A total of 15 patients with benign bone lesions and chronic osteomyelitis were operated and the osseous defects were filled with calcium sulfate which was comprehensively sterilized. Patients were followed with serial radiographs at six week intervals. Calcium sulfate resorption and new bone formation was studied. Results: Thirteen cases out of 15 showed calcium sulphate resorption and new bone incorporation. Calcaium sulphate resorption occurred at an average of 14.5 weeks (range,13-18weeks) whereas new bone incorporation occurred at an average of 6months ( range,5-7months). Thirteen patients out of these 15 cases returned to full activities of daily living. One patient had pathological fracture at the osseous defect postoperatively. One patient with GCT of distal end of tibia had recurrence of tumor and had to undergo second surgery. Conclusion: Although autogenous bone graft is the gold standard for bone grafting, it has limitations like finite amount, additional surgery and donor site morbidity. Calcium sulphate is safe, efficient and easily available bone graft substitute in the treatment of osseous defects. Most common complication encountered was aseptic serous discharge. Functional results were favorable in most of the cases.

Iris biometric entails using the patterns on the iris as a biometric for personal authentication. It has additional benefits over contact-based biometrics such as fingerprints and hand geometry. However, iris biometric often suffers from the following three challenges: ability to handle unconstrained acquisition, privacy enhancement without compromising security, and robust matching. This chapter discusses a unified framework based on sparse representations and random projections that can address these issues simultaneously. Furthermore, recognition from iris videos as well as generation of cancelable iris templates for enhancing the privacy and security is also discussed.

A reliable method for extracting structural features from fingerprint images is presented. Viewing fingerprint images as a textured image, an orientation flow field is computed. The rest of the stages in the algorithm use the flow field to design adaptive filters for the input image. To accurately locate ridges, a waveform projection-based ridge segmentation algorithm is used. The ridge skeleton image is obtained and smoothed using morphological operators to detect the features. A large number of spurious features from the detected set of minutiae is deleted by a postprocessing stage. The performance of the proposed algorithm has been evaluated by computing a “goodness index” (GI) which compares the results of automatic extraction with manually extracted ground truth. The significance of the observed GI values is determined by comparing the index for a set of fingerprints against the GI values obtained under a baseline distribution. The detected features are observed to be reliable and accurate.

Face recognition systems, trained in controlled environment, often fail to efficiently match low resolution images with high resolution images. In this research, a co-transfer learning framework is proposed in which knowledge learnt in controlled high resolution environment is transferred for matching low resolution probe images with high resolution gallery. The proposed framework seamlessly combines transfer learning and co-training to perform knowledge transfer by updating classifier's decision boundary with low resolution probe instances. Experiments are performed on the CMU-Multi-PIE and SCface database with gallery images of size 72 × 72 and size of probe images varying from 48 × 48 to 16 × 16. The results show that, in terms of rank-1 identification accuracy, the proposed algorithm outperforms existing approaches by at least 5%.