A successful deployment of biometric-based recognition systems in real-life applications depends on crucial issues such as data security and privacy, which have to be specifically addressed. Besides, cryptographic key protection can represent the main weakness of a secured transmission. In this demonstration a system for encryption and digital signature of generic digital documents (SAES, standing for Signature-based Assymetric Encryption System) is presented, where cryptographic keys are protected by the hand-written signature of the user. Furthermore, a demonstration of a the handwritten online signature verification system (SVS) based on non-protected templates will also be performed.

This paper presents a smart photo sharing application for mo bile devices based on an efficient yet powerful face recognition engine. The system allows registering subjects either from live video (mobile camera) or from still images, linking the obtained biometric information to the already existing phone contacts. The photo sharing application allows the user to select images which will be automatically processed with the built-in face recognition module based on Local Binary Patterns: already registered contacts will be identified, so that the current picture can be sent to them in a smart, user-friendly manner. The application also allows to tag unknown subjects and store (or update) their biometric profiles. All the processing is done in the mobile device. The current application runs on Android O.S., having been tested in two mobile platforms: HTC Desire and Samsung Galaxy Tab. The computational burden for each of the processing modules is provided in both devices, demonstrating the feasibility of the proposed approach for mobile platforms.

Privacy and security have always been key concerns for individuals. They have also been closely related concepts: in order to increase their perception of security, people sacrifice a part of their privacy by accepting to be surveilled by others. The tradeoff between both is usually reasonable and commonly accepted; however, the case of videosurveillance systems has been particularly controversial since their inception, as their benefits are not perceived to compensate for the privacy loss in many cases. The situation has become even worse during the last years with the massive deployment of these systems, which often do not provide satisfactory guarantees for the citizens. This paper proposes a DRM-based framework for videosurveillance to achieve a better balance between both concepts: it protects privacy of the surveilled individuals, whilst giving support to efficient automated surveillance.

This paper presents both theoretical and practical analyses of the security offered by watermarking and data hiding methods based on spread spectrum. In this context, security is understood as the difficulty of estimating the secret parameters of the embedding function based on the observation of watermarked signals. On the theoretical side, the security is quantified from an information-theoretic point of view by means of the equivocation about the secret parameters. The main results reveal fundamental limits and bounds on security and provide insight into other properties, such as the impact of the embedding parameters, and the tradeoff between robustness and security. On the practical side, workable estimators of the secret parameters are proposed and theoretically analyzed for a variety of scenarios, providing a comparison with previous approaches, and showing that the security of many schemes used in practice can be fairly low.

This paper presents a security analysis for data-hiding methods based on nested lattice codes, extending the analysis provided by previous works to a more general scenario. The security is quantified as the difficulty of estimating the secret key used in the embedding process, assuming that the attacker has several signals watermarked available with the same secret key. The theoretical analysis accomplished in the first part of this paper quantifies security in an information-theoretic sense by means of the mutual information between the watermarked signals and the secret key, addressing important issues, such as the possibility of achieving perfect secrecy and the impact of the embedding rate in the security level. In the second part, a practical algorithm for estimating the secret key is proposed, and the information extracted is used for implementing a reversibility attack on real images.

Gabor filters are biologically motivated convolution kernels that have been widely used in the field of computer vision and, specially, in face recognition during the last decade. This paper proposes a statistical model of Gabor coefficients extracted from face images using generalized Gaussian distributions (GGD's). By measuring the Kullback-Leibler distance (KLD) between the pdf of the GGD and the relative frequency of the coefficients, we conclude that GGD's provide an accurate modeling. The underlying statistics allow us to reduce the required amount of data to be stored (i.e. data compression) via Lloyd-Max quantization. Verification experiments on the XM2VTS database show that performance does not drop when, instead of the original data, we use quantized coefficients.

Security of quantization index modulation (QIM) watermarking methods is usually sought through a pseudorandom dither signal which randomizes the codebook. This dither plays the role of the secret key (i.e., a parameter only shared by the watermarking embedder and decoder), which prevents unauthorized embedding and/or decoding. However, if the same dither signal is reused, the observation of several watermarked signals can provide sufficient information for an attacker to estimate the dither signal. This paper focuses on the cases when the embedded messages are either known or constant. In the first part of this paper, a theoretical security analysis of QIM data hiding measures the information leakage about the secret dither as the mutual information between the dither and the watermarked signals. In the second part, we show how set-membership estimation techniques successfully provide accurate estimates of the dither from observed watermarked signals. The conclusion of this twofold study is that current QIM watermarking schemes have a relative low security level against this scenario because a small number of observed watermarked signals yields a sufficiently accurate estimate of the secret dither. The analysis presented in this paper also serves as the basis for more involved scenarios

This paper comes to fill a gap in watermarking theory, analyzing the exact performance of the scalar Costa scheme (SCS) facing additive Gaussian attacks when the usual approximation of high-resolution quantization is not valid, thus taking into account the host statistics. The analysis is focused on the assessment of the probability of error, showing new results, an although it is valid in a general scenario, its practical interest is increased when SCS is used in conjunction with the so-called spread-transform. The accomplished reformulation of the problem also permits to show that the achievable rate of SCS is never worse than that of classical spread-spectrum-based methods, as it was thought so far, and allows to establish interesting links with spread spectrum and the Improved Spread Spectrum method.

The paper deals with the task of audio segmentation in TV broadcast news. A multimedia approach for this purpose, by means of audio and video processing, is proposed. Thus, the segmentation system is composed by two differentiated parts: one analyzes the audio stream, and is based on the well-known Bayesian information criterion (BIC), whereas the other part extracts useful information from the video stream to improve the performance of BIC. An investigation of parameters involved in BIC formulation is also accomplished, in order to achieve the best results possible in our experimental framework: the database Transcrigal-DB. The final system provides significative improvements in both overall performance and robustness.

By abandoning the assumption of an infinite document to watermark ratio, we recompute the achievable rates for Egger's scalar Costa scheme (SCS, also known as scalar distortion compensated dither modulation) and show, as opposed to the results reported by Eggers, that the achievable rates of SCS are always larger than those of spread spectrum (SS). Moreover, we show that for small watermark to noise ratios, SCS equivalent to a two-centroid problem, thus revealing interesting relations with SS and with Malvar's improved spread spectrum (ISS). We also show an interesting behavior for the optimal distortion compensation parameter. All these results aim at filling an existing gap in watermarking theory and have important consequences for the design of efficient decoders for data hiding problems.