Dissertations / Theses on the topic 'Authentification biométrique'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 16 dissertations / theses for your research on the topic 'Authentification biométrique.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Keuffer, Julien. "Calcul vérifiable et vérification biométrique." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS156.
Full textThis thesis deals with the notion of verifiable computation, which aims at adding a proof of correctness to the result of a computation. Besides, verifying the proof should be more efficient than executing it. Verifiable computation protocols pave the way for delegation of computations to an untrusted party. The first part of this thesis introduces the background required to understand the most important verifiable computation protocols and describes their construction. Many protocols have been proposed since 2012 and some are nearly practical, but the prover often lacks efficiency. Even though several specialized protocols are very efficient, it seems more appropriate to consider protocols that can verify a large class of computations, in order to avoid the multiplications of proofs for each sub-computation. In the second part of this thesis, we leverage proof composition to obtain a non-interactive verifiable computation protocol with a more efficient prover while keeping the expressiveness of the scheme. Some of the existing verifiable computation systems reach additional properties and provide zero-knowledge for the proof with little overhead for the prover. We propose two applications that leverage this property to design new primitives. This first one enables to modify a signed document while keeping a form of authenticity. The second one allows for a privacy-preserving biometric authentication
Karam, Walid. "Imposture audiovisuelle et robustesse de la vérification de l'identité." Paris, Télécom ParisTech, 2010. http://www.theses.fr/2010ENST0061.
Full textWith the emergence of smart phones and third and fourth generation mobile and communication devices, and the appearance of a "first generation" type of mobile PC/PDA/phones with biometric identity verification, there has been recently a greater attention to secure communication and to guaranteeing the robustness of embedded multi-modal biometric systems. The robustness of such systems promises the viability of newer technologies that involve e-voice signatures, e-contracts that have legal values, and secure and trusted data transfer regardless of the underlying communication protocol. Realizing such technologies require reliable and error-free biometric identity verification systems. The robustness of a biometric identity verification (IV) system is best evaluated by monitoring its behavior under impostor attacks. The purpose of this work is threefold :1. It evaluates the performance of IV systems by monitoring their behavior under impostor attacks. Such attacks may include the transformation of one, many, or all of the biometric modalities, such as face or voice. This thesis provides a brief review of IV techniques and corresponding evaluations, and focuses on a statistical approach (GMM). 2. It introduces MixTrans, a novel mixture-structure bias voice transformation technique in the cepstral domain, which allows a transformed audio signal to be estimated and reconstructed in the temporal domain. The reconstructed "forged" speech signal is audibly perceived, and its effect on the verification system is evaluated. It has been proved that voice transformation that attempts to mimic a target speaker affects the performance of the biometric verification system. 3. It proposes a face transformation technique that allows a 2-D face image of the client to be animated. This technique employs principal warps to deform defined MPEG-4 facial feature points based on determined facial animation parameters (FAP). The BANCA database is used to test the effects of voice and face transformation on the IV system. The proposed audiovisual forgery is completely independent from the baseline audiovisual IV system, and can be used to attack any other audiovisual IV system. The results drawn from the experiments show that the state-of-the-art IV systems are vulnerable to forgery attacks, which indicate more impostor acceptance, and, for the same threshold, more genuine client denial
Wirotius, Matthieu. "Authentification par signature manuscrite sur support nomade." Tours, 2005. http://www.theses.fr/2005TOUR4031.
Full textWork presented in this thesis concerns authentification using on line handwritten signatures. First we studied the caracterisation of signatures by extraction and selection of global features. The new characteristics proposed are based on the study of fractality and multi-resolution of on line handwritten signatures. Then, in order to improve the results obtained by using a method called Dynamic Time Warping, we present some modifications for matching the points of the signature and proposed new methods to compute the distance between signatures using the whole information available. Finally, we construct an architecture that takes into account the constraints of storing the pattern of the signature in a smart card. The tests realised on databases of signatures show the pertinence of our choices
Hocquet, Sylvain. "Authentification biométrique adaptative : application à la dynamique de frappe et à la signature manuscrite." Tours, 2007. http://www.theses.fr/2007TOUR4028.
Full textThe objective of our work is to propose a behavioral biometry system. The first part of this manuscript proposes a state of the art about biometric authentification using behavioral biometrics and one-class problem in order to identify the problems, which remains. The second part presents our propositions. We propose the use of a world model database to allow the adaptation of the system to each user by the determination of personalized parameters. We also study the profile upgrades to keep track of the evolution of the user biometry. The last part of this manuscript presents two applications of our work on biometry authentication system : using keystroke dynamics and on-line handwritten signature. Our experiments show the interest of our recommandations and validate their generality : in both cases, the performances of the behavioral biometric systems increase significantly with our proposition
Chang, Chuan. "Authentification biométrique par dynamique de frappe pour évaluation à distance utilisant SVM à une classe." Master's thesis, Université Laval, 2016. http://hdl.handle.net/20.500.11794/27194.
Full textOne-Class Support Vector Machine is an unsupervised algorithm that learns a decision function from only one class for novelty detection. By training the data with only one class, this method is able to classify new data as similar (inlier) or different (outlier) from the training set. In this thesis, we have applied the One-Class Support Vector Machine to Keystroke Dynamics pattern recognition for user authentication in a remote evaluation system at Laval University. Since all of their students have a short and unique identifier at Laval University, this particular static text is used as the Keystroke Dynamics input for a user to build our own dataset. After training a model for each student with his or her keystroke data, we then use this model to detect imposters in the later phase. Three methods were tried and discussed for the classification. Then, we were able to identify weaknesses of each method in such a system by evaluating the recognition accuracy depending on the number of signatures and as a function of their number of characters. Finally, we were able to show some correlations between the dispersion and mode of distributions of features characterizing the keystroke signatures and the recognition rate.
Abid, Mohamed. "Des mécanismes d’authentification basés sur l’identité de l’utilisateur pour renforcer la sécurité des réseaux." Thesis, Evry, Institut national des télécommunications, 2011. http://www.theses.fr/2011TELE0005/document.
Full textIn this thesis, we design three new authentication mechanisms based on user identity. Therefore, we bring improvements in access control for different classes of networks such as Home Network, Governmental Network and Cellular Network. The identity can be biometric public features, simple strings (email addresses, login...), etc. The first solution concerns the use of biometric in Home Network' authentication mechanisms. In the Home Network (HN) case study, we aim at personalizing the access of each user in the HN and preventing illegitimate users (passing by the Home Gateway (HG)) to have any access. We propose a new biometric authentication method which respects the constraint of the non storage of the users' Biometric Template (BT) in the HG. To satisfy this constraint, we propose using the fuzzy vault method to hide a secret that should be used for authentication. A software generates a revocable biometric identity (BioID) using a functional transformation. This BioID is used in the fuzzy vault mechanisms to hide a secret session key. The second solution proposes e-Passport authentication mechanisms. The cryptographic parameters are generated using the biometric templates and hence, personalized for the user. In travel document case study, we present our proposal which introduces a new e-Passport authentication mechanisms based on the Elliptic Curve Diffie-Hellman (ECDH) Key Agreement protocol. This protocol is needed to generate a session key used to authenticate the traveler and the Inspection System (IS) to exchange secure data. Our protocol is defined using minutiae data (fingerprint) and iris code of the e-Passport holder. In the third solution, we worked on the Cellular Network and we used a simple string, like email addresses, as identifier to access to services. We choose the IP Multimedia Subsystem (IMS) which is an overlay architecture for the provision of multimedia services. We design a new service authentication mechanism relying on Identity Based Cryptography (IBC) for the IMS architecture. The goal was to authenticate the users using their public and private identifiers to overcome known weaknesses in the Authentication and Key Agreement (AKA) protocol. We focused on the eavesdropping and impersonation attacks that can take place in classical IMS scenario and we showed how our proposed solution can prevent against these attacks. We, then, proposed to add a Batch Verification on the Bootstrapping Server Function (BSF) to decrease signature verification delay and the authentication response time
Abid, Mohamed. "Des mécanismes d'authentification basés sur l'identité de l'utilisateur pour renforcer la sécurité des réseaux." Phd thesis, Institut National des Télécommunications, 2011. http://tel.archives-ouvertes.fr/tel-00629931.
Full textBardou, Sophie. "Les traitements de données biométriques en entreprise." Thesis, Montpellier 1, 2010. http://www.theses.fr/2010MON10031/document.
Full textBiometry brings together computing techniques that enable the identification of individuals on the basis of their biological, physical appearance and/or behavioral characteristics. Although firstly reserved for the legal system/judiciary domain, biometry tends to be generalized in all spheres of people life. Recently, biometry has also been used in companies who are always receptive to new technologies. Thus, the introduction of identifying devices such as these into a company life has to be the subject of corporate discussions between the managing teams and staff representatives. Indeed, such technologies are often compared to video surveillance, RFID chips, GPS data … and they can lead to the spying of employees if their uses are not well supervised. In the absence of specific laws, the legislator has given the CNIL the abilities to establish the requirements of eligibility of this technology usage within the companies. The "liberty and computing" legislation is then combined with the labor laws in order to apply common principles such as the finality, the proportionality, the loyalty, the transparency of information and employee consents
Abid, Mohamed. "Des mécanismes d’authentification basés sur l’identité de l’utilisateur pour renforcer la sécurité des réseaux." Electronic Thesis or Diss., Evry, Institut national des télécommunications, 2011. http://www.theses.fr/2011TELE0005.
Full textIn this thesis, we design three new authentication mechanisms based on user identity. Therefore, we bring improvements in access control for different classes of networks such as Home Network, Governmental Network and Cellular Network. The identity can be biometric public features, simple strings (email addresses, login...), etc. The first solution concerns the use of biometric in Home Network' authentication mechanisms. In the Home Network (HN) case study, we aim at personalizing the access of each user in the HN and preventing illegitimate users (passing by the Home Gateway (HG)) to have any access. We propose a new biometric authentication method which respects the constraint of the non storage of the users' Biometric Template (BT) in the HG. To satisfy this constraint, we propose using the fuzzy vault method to hide a secret that should be used for authentication. A software generates a revocable biometric identity (BioID) using a functional transformation. This BioID is used in the fuzzy vault mechanisms to hide a secret session key. The second solution proposes e-Passport authentication mechanisms. The cryptographic parameters are generated using the biometric templates and hence, personalized for the user. In travel document case study, we present our proposal which introduces a new e-Passport authentication mechanisms based on the Elliptic Curve Diffie-Hellman (ECDH) Key Agreement protocol. This protocol is needed to generate a session key used to authenticate the traveler and the Inspection System (IS) to exchange secure data. Our protocol is defined using minutiae data (fingerprint) and iris code of the e-Passport holder. In the third solution, we worked on the Cellular Network and we used a simple string, like email addresses, as identifier to access to services. We choose the IP Multimedia Subsystem (IMS) which is an overlay architecture for the provision of multimedia services. We design a new service authentication mechanism relying on Identity Based Cryptography (IBC) for the IMS architecture. The goal was to authenticate the users using their public and private identifiers to overcome known weaknesses in the Authentication and Key Agreement (AKA) protocol. We focused on the eavesdropping and impersonation attacks that can take place in classical IMS scenario and we showed how our proposed solution can prevent against these attacks. We, then, proposed to add a Batch Verification on the Bootstrapping Server Function (BSF) to decrease signature verification delay and the authentication response time
Guerfi, Souhila. "Authentification d'individus par reconnaissance de caractéristiques biométriques liées aux visages 2D/3D." Phd thesis, Université d'Evry-Val d'Essonne, 2008. http://tel.archives-ouvertes.fr/tel-00623243.
Full textGuerfi, Ababsa Souhila. "Authentification d’individus par reconnaissance de caractéristiques biométriques liées aux visages 2D/3D." Thesis, Evry-Val d'Essonne, 2008. http://www.theses.fr/2008EVRY0032/document.
Full textThis thesis deals with the face authentification problem, in particular within a national project framework, namely "TechnoVision". Although the human beings can detect/recognise faces in a scene without much of sorrow, build a system which achieves such tasks is very challenging. This challenge is all the more large when the conditions of images acquisition are variable. There are two kinds of variations associated to the face images: inter and intra subject. The inter-subject variation is limited because owing to the fact that the physical resemblance between the individuals is rather rare. On the other hand, the intra-subject variation is more current because of pose changing, lighting conditions, etc. In this thesis, we developed, first, an approach for face and facial features localization in images containing only one face on a relatively uniform background within light variations. For that we proposed a robust colour segmentation approach in the TLS space which uses a modified watershed algorithm. To extract the facial features (like eyes and stops), we combined a kmeans clustering method with a geometrical approach and applied it on the segmented region of the face. We also proposed a 2D/3D multimodal approach which uses a weighted fusion of the scores obtained by the modular “EigenFace” and our 3D anthropometric facial signature. We evaluated our 3D and 2D/3D face recognition approaches on a sub base of IV2 which contains stereoscopic images of several human faces. The obtained results are very interesting compared to classical techniques of 2D face recognition. Finally, we discussed how to improve the performances of the proposed approaches
Huet, Romain. "Reconnaissance de gestes et communication intra-corps sécurisée." Electronic Thesis or Diss., Université de Lorraine, 2021. http://www.theses.fr/2021LORR0050.
Full textThis thesis presents the development of a new biometrics approach based on IntraBody Communication (IBC). The human body is seen as a transmission medium for the electric signals. Is that transmission medium discriminant enough in order to use it as a biometric identifier? The hypothesis is that the body and its mouvments can modulate a signal in a specific way and it can contribute to creating an individual signature. For instance, it could be used to secure transfers like payments. Three main components have been studied. The first one is a bibliographic analysis. In studying what already exists in diffrent fields, the idea here is to create a prototype that can measure the signals modified by the human body. This prototype is the key to success, because all the results depend on the quality of that receiver. The next component is to study the received signal measured by the prototype we created during the approach phase of the hand toward the emitter. IntraBody Communication is seen as a behavioural biometrics in this part. The signature is based on the hand motion. The last part is more about the physiological properties of the human body. Is it possible to find specific characteristics, in the signal measured by the prototpye, in order to identify or authenticate someone? The human body is studied as a static system and we attempt to characterize it with some classical methods
Tak, Hemlata. "End-to-End Modeling for Speech Spoofing and Deepfake Detection." Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS104.pdf.
Full textVoice biometric systems are being used in various applications for secure user authentication using automatic speaker verification technology. However, these systems are vulnerable to spoofing attacks, which have become even more challenging with recent advances in artificial intelligence algorithms. There is hence a need for more robust, and efficient detection techniques. This thesis proposes novel detection algorithms which are designed to perform reliably in the face of the highest-quality attacks. The first contribution is a non-linear ensemble of sub-band classifiers each of which uses a Gaussian mixture model. Competitive results show that models which learn sub-band specific discriminative information can substantially outperform models trained on full-band signals. Given that deep neural networks are more powerful and can perform both feature extraction and classification, the second contribution is a RawNet2 model. It is an end-to-end (E2E) model which learns features directly from raw waveform. The third contribution includes the first use of graph neural networks (GNNs) with an attention mechanism to model the complex relationship between spoofing cues present in spectral and temporal domains. We propose an E2E spectro-temporal graph attention network called RawGAT-ST. RawGAT-ST model is further extended to an integrated spectro-temporal graph attention network, named AASIST which exploits the relationship between heterogeneous spectral and temporal graphs. Finally, this thesis proposes a novel data augmentation technique called RawBoost and uses a self-supervised, pre-trained speech model as a front-end to improve generalisation in the wild conditions
El, Khoury Franjieh. "Modélisation de la sécurisation d’accès aux réseaux par la technique de cryptographie asymétrique en utilisant la reconnaissance de l’iris et la technologie des agents." Thesis, Lyon 1, 2009. http://www.theses.fr/2009LYO10308.
Full textThe exponential growth in the use of the Internet as well as the emergence of new types of applications has increased the network’s constraints in terms f security. Fort the last several years, biometric techniques have proven their applicability and reliability in providing secure access to shared resources in different domains. Furthermore, software agents and multi-agent systems (MAS) have evidently been efficient in resolving several problems in network. Therefore, the aim of this research is to propose a model “IrisCryptoAgentSystem” (ICAS) that is based on a biometric method for authentication using the iris of the eyes and an asymmetric cryptography method using “Rivest-Shamir-Adleman” (RSA) in an agent-based architecture. This model should provide secure access to information and ensure the protection of confidential information. Therefore, our work focuses on the development of new methods in biometric autheitcation in order to provide greater efficiency in the ICAS model. We introduce pretopological aspects in the development of the indexed hierarchy to classify DHVA templates. Our approach aims to improve the existing methods for the localization of the external and the internal edges of the iris
Trabelsi, Anis. "Robustesse aux attaques en authentification digitale par apprentissage profond." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS580.
Full textThe identity of people on the Internet is becoming a major security issue. Since the Bale agreements, banking institutions have integrated the verification of people's identity or Know Your Customer (KYC) in their registration process. With the dematerialization of banks, this procedure has become e-KYC or remote KYC which works remotely through the user's smartphone. Similarly, remote identity verification has become the standard for enrollment in electronic signature tools. New regulations are emerging to secure this approach, for example, in France, the PVID framework regulates the remote acquisition of identity documents and people's faces under the eIDAS regulation. This is required because a new type of digital crime is emerging: deep identity theft. With new deep learning tools, imposters can change their appearance to look like someone else in real time. Imposters can then perform all the common actions required in a remote registration without being detected by identity verification algorithms. Today, smartphone applications and tools for a more limited audience exist allowing imposters to easily transform their appearance in real time. There are even methods to spoof an identity based on a single image of the victim's face. The objective of this thesis is to study the vulnerabilities of remote identity authentication systems against new attacks in order to propose solutions based on deep learning to make the systems more robust
Woodtli, Patrick F. "Cerbère au temps des " bio-maîtres " : la biométrie, servante-maîtresse d'une nouvelle ère biopolitique ? Le cas du programme US-VISIT." Thèse, 2008. http://hdl.handle.net/1866/7324.
Full text