Presentation attack detection is a challenging problem that aims at exposing an impostor user seeking to deceive the authentication system. In facial biometrics systems, this kind of attack is performed using a photograph, video, or 3D mask containing the biometric information of a genuine identity. In this paper, we propose a novel approach to detecting face presentation attacks based on intrinsic properties of the scene such as albedo, depth, and reflectance properties of the facial surfaces, which were recovered through a shape-from-shading (SfS) algorithm. To extract meaningful patterns from the different maps obtained with the SfS algorithm, we designed a novel shallow CNN architecture for learning features useful to the presentation attack detection (PAD). We performed several experiments considering the intra- and inter-dataset evaluation protocols. The obtained results showed the effectiveness of the proposed method considering several types of photo- and video-based presentation attacks, and in the cross-sensor scenario, besides achieving competitive results for the inter-dataset evaluation protocol.

Fake news and deep fakes have been making social and mainstream media headlines. At the same time, engaged scientists strive for finding ways to detect forgeries and suspicious manipulations using even the subtlest clues. In this vein, this work proposes a new method for detecting photographic splicing by bringing together the high representation power of Illuminant Maps and Convolutional Neural Networks as a way of learning directly from available training data the most important hints of a forgery. This work propose a method that eliminates the laborious feature engineering process, allow locate forgery region and yields a classification accuracy of more than 96%, outperforming state-of-the-art methods in different datasets. The potential uses of the proposed method is further highlighted by analyzing some suspicious real-world photographs that recently broke the news.

The advance of computer graphics techniques comes revolutionizing games and movie's industries. Creating very realistic characters totally from computer graphics models is, nowadays, a reality. However, this advance comes with a big price: the realism of images is so big that it is difficult to realize when we are facing a computer generated image or a real photo. In this paper we propose a new approach for highly realistic computer generated images detection by exploring inconsistencies into the region of the eyes. Such inconsistencies are captured exploring the expression power of features extracted via transfer learning approach with VGG19 Deep Neural Network model. Unlike the state-of-the-art approaches, which looks to evaluate the entire image, proposed method focuses in specific regions (eyes) where computer graphics modeling still needs improvements. Experiments conducted over two different datasets containing extremely realistic images achieved an accuracy of 0.80 and an AUC of 0.88.

Malicious software (malware) has been extensively used for illegal activity and new malware variants are discovered at an alarmingly high rate. The ability to group malware variants into families with similar characteristics makes possible to create mitigation strategies that work for a whole class of programs. In this paper, we present a malware family classification approach using a deep neural network based on the ResNet-50 architecture. Malware samples are represented as byteplot grayscale images and a deep neural network is trained freezing the convolutional layers of ResNet-50 pre-trained on the ImageNet dataset and adapting the last layer to malware family classification. The experimental results on a dataset comprising 9,339 samples from 25 different families showed that our approach can effectively be used to classify malware families with an accuracy of 98.62%.

Geographical information systems-based methods can be handled as powerful tools in assessing and quantifying impacts and, thus, supporting strategies for disaster risk reduction (DRR). This is particularly relevant on scenarios of global climate change and intensified increased human interventions on riverine systems. The Madeira River in Porto Velho city (Brazilian Amazon) is a good example of susceptible area to both of these factors. We take advantage of the 2014 flood, the largest recorded for this region, for combining remote sensing and geographic information system with socio, health, and infrastructure data to quantify spatially the flood impacts. Using high resolution airborne images, we applied a machine learning classification algorithm for detecting urban areas. Our results show that at the flood extent related to the highest river level at least 0.65$\text {km}^{2}$of urban area, 87 km of urban streets, four public schools, and two public health units were affected. More than 16 800 people suffered the impacts directly, and children represented 29.7% of them. Based on registered data, it was quantified that the city registered more than 20 cases of leptospirosis and the truck flow on the region decreased up to 92%. The spatially-explicit results of this letter are potential to guide strategies aiming to support decision-making for DRR.