Sylvio Barbon

Authorship verification applied to detection of compromised accounts on online social networks

Compromising legitimate accounts has been the most used strategy to spread malicious content on OSN (Online Social Network). To address this problem, we propose a pure text mining approach to check if an account has been compromised based on its posts content. In the first step, the proposed approach extracts the writing style from the user account. The second step comprehends the k-Nearest Neighbors algorithm (k-NN) to evaluate the post content and identify the user. Finally, Baseline Updating (third step) consists of a continuous updating of the user baseline to support the current trends and seasonality issues of user’s posts. Experiments were carried out using a dataset from Twitter composed by tweets of 1000 users. All the three steps were individually evaluated, and the results show that the developed method is stable and can detect the compromised accounts. An important observation is the Baseline Updating contribution, which leads to an enhancement of accuracy superior of 60 %. Regarding average accuracy, the developed method achieved results over 93 %.

Account classification in online social networks with LBCA and wavelets

We developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each users account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%.

Anomaly detection using the correlational paraconsistent machine with digital signatures of network segment

Abstract This study presents the correlational paraconsistent machine (CPM), a tool for anomaly detection that incorporates unsupervised models for traffic characterization and principles of paraconsistency, to inspect irregularities at the network traffic flow level. The CPM is applied for the mathematical foundation of uncertainties that may arise when establishing normal network traffic behavior profiles, providing means to support the consistency of the information sources chosen for anomaly detection. The experimental results from a real traffic trace evaluation suggest that CPM responses could improve anomaly detection rates.

Predicting the ripening of papaya fruit with digital imaging and random forests

Abstract Papaya grading is performed manually which may lead to misclassifications, resulting in fruit boxes with different maturity stages. The objective is to predict the ripening of the papaya fruit using digital imaging and random forests. A series of physical/chemical analyses are carried out and true maturity stage is derived from pulp firmness measurements. Imaging and image analysis provides hand-crafted color features computed from the peel and random decision forests are implemented to predict ripening stage. More specifically, a total of 114 samples from 57 fruits are used for the experiments, and classified into three stages of maturity. After image acquisition and analysis, twenty-one hand-crafted color features (comprising seven groups) that have low computational cost are extracted and evaluated. Random forests with two datasets (cross-validation and prediction set) are employed for the experiments. Concerning all image features, 94.3% classification performance is obtained over the cross-validation set. The prediction set obtained 94.7% misclassifying only a single sample. For the group comparisons, the normalized mean of the RGB (red, green, blue) color space achieved better performance (78.1%). Essentially, the technique can mature into an industrial application with the right integration framework.

Color energy as a seed descriptor for image segmentation with region growing algorithms on skin wound images

This paper presents a seed finding method for region growing segmentation approach using color channel energy in image regions. Instead of using the RGB system separated for each pixel, the proposal uses the energy on each color channel to improve the range of the possible values, then creates a more specific seed to detail different regions. Region size used to calculate energy was adjusted to verify the proposed method. Images used were real wound photos, taken from patients undergoing treatment at the university hospital. Results showed that energy on regions presents enough information to segment, leading to a high percentage of matching with experts marks.

Introducing the Discriminative Paraconsistent Machine (DPM)

This paper introduces a new tool for pattern recognition. Called the Discriminative Paraconsistent Machine (DPM), it is based on a supervised discriminative model training that incorporates paraconsistency criteria and allows an intelligent treatment of contradictions and uncertainties. DPMs can be applied to solve problems in many fields of science, using the tests and discussions presented here, which demonstrate their efficacy and usefulness. Major difficulties and challenges that were overcome consisted basically in establishing the proper model with which to represent the concept of paraconsistency.

Detecting mobile botnets through machine learning and system calls analysis

Botnets have been a serious threat to the Internet security. With the constant sophistication and the resilience of them, a new trend has emerged, shifting botnets from the traditional desktop to the mobile environment. As in the desktop domain, detecting mobile botnets is essential to minimize the threat that they impose. Along the diverse set of strategies applied to detect these botnets, the ones that show the best and most generalized results involve discovering patterns in their anomalous behavior. In the mobile botnet field, one way to detect these patterns is by analyzing the operation parameters of this kind of applications. In this paper, we present an anomaly-based and host-based approach to detect mobile botnets. The proposed approach uses machine learning algorithms to identify anomalous behaviors in statistical features extracted from system calls. Using a self-generated dataset containing 13 families of mobile botnets and legitimate applications, we were able to test the performance of our approach in a close-to-reality scenario. The proposed approach achieved great results, including low false positive rates and high true detection rates.

Pattern Recognition of Lower Member Skin Ulcers in Medical Images with Machine Learning Algorithms

Misleading diagnosis of skin diseases may result in complications during the healing process. Skin images provide an important contribution to medical staff on storing and exchanging information to try preventing misdiagnosis. For such, image segmentation process may benefit from use of machine learning techniques, increasing simplicity of procedure, reducing computational costs and improving the diagnosis. This paper presents a comparison among different paradigms of machine learning to validate the segmentation of medical images of lower members ulcers, this segmentation allows wound pattern recognition to determinate injury region aiming at reducing the subjectivity of human evaluation.

Adaptive Distribution of Vocabulary Frequencies: A Novel Estimation Suitable for Social Media Corpus

This paper aims to propose a mathematical model that evaluates the distribution of the vocabulary frequency terms in proportion to a probabilistic ideal. Once we are able to evaluate it, the main objective of this work is to use it in order to examine text demising. We propose this new metric based on the classic Zipfs law statistic method. The experimental set to test the classic Zipfs law and our developed model is based on some books of the classic literature and some tweets sets of Twitter. Thus, our main result is that the model proposed in this work is more sensitive to the presence of text noises than Zipfs law and is asymptotically quicker, suitable to corpus of social media networks.

Support vector machines and wavelets for voice disorder sorting

We present an algorithm to distinguish between pathological and normal human voice signals based on discrete wavelet transforms (DWT) and support vector machines (SVM). The former is used for time-frequency analysis and provides quantitative evaluation of signal characteristics. The latter is used for the final classification. The technique leads to an adequate larynx pathology classifier with over 95% of classification accuracy