Comprehensive Vulnerability Evaluation of Face Recognition Systems to Template Inversion Attacks via 3D Face Reconstruction.

In this article, we comprehensively evaluate the vulnerability of state-of-the-art face recognition systems to template inversion attacks using 3D face reconstruction. We propose a new method (called GaFaR) to reconstruct 3D faces from facial templates using a pretrained geometry-aware face generation network, and train a mapping from facial templates to the intermediate latent space of the face generator network. We train our mapping with a semi-supervised approach using real and synthetic face images. For real face images, we use a generative adversarial network (GAN)-based framework to learn the distribution of generator intermediate latent space. For synthetic face images, we directly learn the mapping from facial templates to the generator intermediate latent code. Furthermore, to improve the success attack rate, we use two optimization methods on the camera parameters of the GNeRF model. We propose our method in the whitebox and blackbox attacks against face recognition systems and compare the transferability of our attack with state-of-the-art methods across other face recognition systems on the MOBIO and LFW datasets. We also perform practical presentation attacks on face recognition systems using the digital screen replay and printed photographs, and evaluate the vulnerability of face recognition systems to different template inversion attacks.

Autologous Mesenchymal Stem Cells Improve Motor Recovery in Subacute Ischemic Stroke: a Randomized Clinical Trial.

While preclinical stroke studies have shown that mesenchymal stem cells (MSCs) promote recovery, few randomized controlled trials (RCT) have assessed cell therapy in humans. In this RCT, we assessed the safety, feasibility, and efficacy of intravenous autologous bone marrow-derived MSCs in subacute stroke. ISIS-HERMES was a single-center, open-label RCT, with a 2-year follow-up. We enrolled patients aged 18-70 years less than 2 weeks following moderate-severe ischemic carotid stroke. Patients were randomized 2:1 to receive intravenous MSCs or not. Primary outcomes assessed feasibility and safety. Secondary outcomes assessed global and motor recovery. Passive wrist movement functional MRI (fMRI) activity in primary motor cortex (MI) was employed as a motor recovery biomarker. We compared "treated" and "control" groups using as-treated analyses. Of 31 enrolled patients, 16 patients received MSCs. Treatment feasibility was 80%, and there were 10 and 16 adverse events in treated patients, and 12 and 24 in controls at 6-month and 2-year follow-up, respectively. Using mixed modeling analyses, we observed no treatment effects on the Barthel Index, NIHSS, and modified-Rankin scores, but significant improvements in motor-NIHSS (p = 0.004), motor-Fugl-Meyer scores (p = 0.028), and task-related fMRI activity in MI-4a (p = 0.031) and MI-4p (p = 0.002). Intravenous autologous MSC treatment following stroke was safe and feasible. Motor performance and task-related MI activity results suggest that MSCs improve motor recovery through sensorimotor neuroplasticity. ClinicalTrials.gov Identifier NCT00875654.

Safety of Intravenous Immunoglobulin (Tegeline®), Administered at Home in Patients with Autoimmune Disease: Results of a French Study.

The efficacy of intravenous immunoglobulins (IVIg) in patients with autoimmune diseases (AID) has been known for several decades. Majority of these patients received IVIg in hospital. A retrospective study was conducted in 22 centers in France to evaluate the feasibility of the administration of Tegeline, an IVIg from LFB Biomedicaments, and assess its safety at home, compared to in hospital, in patients with AID. The included patients were at least 18 years old, suffering from AID, and treated with at least 1 cycle of Tegeline at home after receiving 3 consecutive cycles of hospital-based treatment with Tegeline at a dose between 1 and 2 g/kg/cycle. Forty-six patients with AID, in most cases immune-mediated neuropathies, received a total of 138 cycles of Tegeline in hospital and then 323 at home. Forty-five drug-related adverse events occurred in 17 patients who received their cycles at home compared to 24 adverse events in hospital in 15 patients. Serious adverse events occurred in 3 patients during home treatment, but they were not life-threatening and did not lead to discontinuation of Tegeline. Forty-five patients continued their treatment with Tegeline at home or in hospital; 39 (84.8%) were still receiving home treatment at the end of the study. In conclusion, the study demonstrates the good safety profile of Tegeline administered at home at high doses in patients with AID who are eligible for home administration of Tegeline.

Image Quality Assessment for Fake Biometric Detection: Application to Iris, Fingerprint, and Face Recognition.

To ensure the actual presence of a real legitimate trait in contrast to a fake self-manufactured synthetic or reconstructed sample is a significant problem in biometric authentication, which requires the development of new and efficient protection measures. In this paper, we present a novel software-based fake detection method that can be used in multiple biometric systems to detect different types of fraudulent access attempts. The objective of the proposed system is to enhance the security of biometric recognition frameworks, by adding liveness assessment in a fast, user-friendly, and non-intrusive manner, through the use of image quality assessment. The proposed approach presents a very low degree of complexity, which makes it suitable for real-time applications, using 25 general image quality features extracted from one image (i.e., the same acquired for authentication purposes) to distinguish between legitimate and impostor samples. The experimental results, obtained on publicly available data sets of fingerprint, iris, and 2D face, show that the proposed method is highly competitive compared with other state-of-the-art approaches and that the analysis of the general image quality of real biometric samples reveals highly valuable information that may be very efficiently used to discriminate them from fake traits.

A scalable formulation of probabilistic linear discriminant analysis: applied to face recognition.

In this paper, we present a scalable and exact solution for probabilistic linear discriminant analysis (PLDA). PLDA is a probabilistic model that has been shown to provide state-of-the-art performance for both face and speaker recognition. However, it has one major drawback: At training time estimating the latent variables requires the inversion and storage of a matrix whose size grows quadratically with the number of samples for the identity (class). To date, two approaches have been taken to deal with this problem, to 1) use an exact solution that calculates this large matrix and is obviously not scalable with the number of samples or 2) derive a variational approximation to the problem. We present a scalable derivation which is theoretically equivalent to the previous nonscalable solution and thus obviates the need for a variational approximation. Experimentally, we demonstrate the efficacy of our approach in two ways. First, on labeled faces in the wild, we illustrate the equivalence of our scalable implementation with previously published work. Second, on the large Multi-PIE database, we illustrate the gain in performance when using more training samples per identity (class), which is made possible by the proposed scalable formulation of PLDA.

Human endogenous retrovirus type W envelope expression in blood and brain cells provides new insights into multiple sclerosis disease.

BACKGROUND: The envelope protein from multiple sclerosis (MS) associated retroviral element (MSRV), a member of the Human Endogenous Retroviral family 'W' (HERV-W), induces dysimmunity and inflammation. OBJECTIVE: The objective of this study was to confirm and specify the association between HERV-W/MSRV envelope (Env) expression and MS. METHODS: 103 MS, 199 healthy controls (HC) and controls with other neurological diseases (28), chronic infections (30) or autoimmunity (30) were analysed with an immunoassay detecting Env in serum. Env RNA or DNA copy numbers in peripheral blood mononuclear cells (PBMC) were determined by a quantitative polymerase chain reaction (PCR). Env was detected by immunohistology in the brains of patients with MS with three specific monoclonals. RESULTS: Env antigen was detected in a serum of 73% of patients with MS with similar prevalence in all clinical forms, and not in chronic infection, systemic lupus, most other neurological diseases and healthy donors (p<0.01). Cases with chronic inflammatory demyelinating polyneuropathy (5/8) and rare HC (4/103) were positive. RNA expression in PBMC and DNA copy numbers were significantly elevated in patients with MS versus HC (p<0.001). In patients with MS, DNA copy numbers were significantly increased in chronic progressive MS (secondary progressive MS vs relapsing-remitting MS (RRMS) p<0.001; primary progressive MS vs RRMS -<0.02). Env protein was evidenced in macrophages within MS brain lesions with particular concentrations around vascular elements. CONCLUSION: The association between MS disease and the MSRV-type HERV-W element now appears quite strong, as evidenced ex-vivo from serum and PBMC with post-mortem confirmation in brain lesions. Chronic progressive MS, RRMS and clinically isolated syndrome show different ELISA (Enzyme-Linked Immunosorbent Assay) and/or PCR profiles suggestive of an increase with disease evolution, and amplicon sequencing confirms the association with particular HERV-W elements.

Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation.

In this paper, we investigate the use of brain activity for person authentication. It has been shown in previous studies that the brain-wave pattern of every individual is unique and that the electroencephalogram (EEG) can be used for biometric identification. EEG-based biometry is an emerging research topic and we believe that it may open new research directions and applications in the future. However, very little work has been done in this area and was focusing mainly on person identification but not on person authentication. Person authentication aims to accept or to reject a person claiming an identity, i.e., comparing a biometric data to one template, while the goal of person identification is to match the biometric data against all the records in a database. We propose the use of a statistical framework based on Gaussian Mixture Models and Maximum A Posteriori model adaptation, successfully applied to speaker and face authentication, which can deal with only one training session. We perform intensive experimental simulations using several strict train/test protocols to show the potential of our method. We also show that there are some mental tasks that are more appropriate for person authentication than others.

Culture-negative endocarditis due to Houston Complex Bartonella henselae acquired in Noumea, New Caledonia.

A 44-year-old man with a bioprosthetic aortic valve suffered destructive endocarditis with severe embolic disease due to Bartonella henselae infection. Multilocus sequence typing was successfully performed with crude preparations of operative tissue as templates, and the infecting organism was determined to be typical of the Houston clonal group, although it was never cultured from blood or tissue. This is the first report of B. henselae infection in the South Pacific, and it reminds one that B. henselae is a cause of potentially lethal culture-negative endocarditis which may respond poorly to conventional empirical therapy. Nothing is known of the epidemiology of the infection in this region, but it is likely to be common and to contain representatives of both major clonal complexes. This study emphasizes the ease with which multilocus sequence typing can be used directly with tissue, which is important because of suggestions of strain-dependent clinical outcomes.