Secure data science, which integrates cyber security and data science, is becoming one of the critical areas in both cyber security and data science. This is because the novel data science techniques being developed have applications in solving such cyber security problems as intrusion detection, malware analysis, and insider threat detection. However, the data science techniques being applied not only for cyber security but also for every application area-including healthcare, finance, manufacturing, and marketing-could be attacked by malware. Furthermore, due to the power of data science, it is now possible to infer highly private and sensitive information from public data, which could result in the violation of individual privacy. This is the first such book that provides a comprehensive overview of integrating both cyber security and data science and discusses both theory and practice in secure data science. After an overview of security and privacy for big data services as well as cloud computing, this book describes applications of data science for cyber security applications. It also discusses such applications of data science as malware analysis and insider threat detection. Then this book addresses trends in adversarial machine learning and provides solutions to the attacks on the data science techniques. In particular, it discusses some emerging trends in carrying out trustworthy analytics so that the analytics techniques can be secured against malicious attacks. Then it focuses on the privacy threats due to the collection of massive amounts of data and potential solutions. Following a discussion on the integration of services computing, including cloud-based services for secure data science, it looks at applications of secure data science to information sharing and social media. This book is a useful resource for researchers, software developers, educators, and managers who want to understand both the high level concepts and the technical details on the design and implementation of secure data science-based systems. It can also be used as a reference book for a graduate course in secure data science. Furthermore, this book provides numerous references that would be helpful for the reader to get more details about secure data science.

Analyzing and Securing Social Networks focuses on the two major technologies that have been developed for online social networks (OSNs): (i) data mining technologies for analyzing these networks and extracting useful information such as location, demographics, and sentiments of the participants of the network, and (ii) security and privacy technologies that ensure the privacy of the participants of the network as well as provide controlled access to the information posted and exchanged by the participants. The authors explore security and privacy issues for social media systems, analyze such systems, and discuss prototypes they have developed for social media systems whose data are represented using semantic web technologies. These experimental systems have been developed at The University of Texas at Dallas. The material in this book, together with the numerous references listed in each chapter, have been used for a graduate-level course at The University of Texas at Dallas on analyzing and securing social media. Several experimental systems developed by graduate students are also provided. The book is divided into nine main sections: (1) supporting technologies, (2) basics of analyzing and securing social networks, (3) the authors' design and implementation of various social network analytics tools, (4) privacy aspects of social networks, (5) access control and inference control for social networks, (6) experimental systems designed or developed by the authors on analyzing and securing social networks, (7) social media application systems developed by the authors, (8) secure social media systems developed by the authors, and (9) some of the authors' exploratory work and further directions.

With an ever-increasing amount of information on the web, it is critical to understand the pedigree, quality, and accuracy of your data. Using provenance, you can ascertain the quality of data based on its ancestral data and derivations, track back to sources of errors, allow automatic re-enactment of derivations to update data, and provide attribution of the data source. Secure Data Provenance and Inference Control with Semantic Web supplies step-by-step instructions on how to secure the provenance of your data to make sure it is safe from inference attacks. It details the design and implementation of a policy engine for provenance of data and presents case studies that illustrate solutions in a typical distributed health care system for hospitals. Although the case studies describe solutions in the health care domain, you can easily apply the methods presented in the book to a range of other domains. The book describes the design and implementation of a policy engine for provenance and demonstrates the use of Semantic Web technologies and cloud computing technologies to enhance the scalability of solutions. It covers Semantic Web technologies for the representation and reasoning of the provenance of the data and provides a unifying framework for securing provenance that can help to address the various criteria of your information systems. Illustrating key concepts and practical techniques, the book considers cloud computing technologies that can enhance the scalability of solutions. After reading this book you will be better prepared to keep up with the on-going development of the prototypes, products, tools, and standards for secure data management, secure Semantic Web, secure web services, and secure cloud computing.

With an ever-increasing amount of information on the web, it is critical to understand the pedigree, quality, and accuracy of your data. Using provenance, you can ascertain the quality of data based on its ancestral data and derivations, track back to sources of errors, allow automatic re-enactment of derivations to update data, and provide attribution of the data source. Secure Data Provenance and Inference Control with Semantic Web supplies step-by-step instructions on how to secure the provenance of your data to make sure it is safe from inference attacks. It details the design and implementation of a policy engine for provenance of data and presents case studies that illustrate solutions in a typical distributed health care system for hospitals. Although the case studies describe solutions in the health care domain, you can easily apply the methods presented in the book to a range of other domains. The book describes the design and implementation of a policy engine for provenance and demonstrates the use of Semantic Web technologies and cloud computing technologies to enhance the scalability of solutions. It covers Semantic Web technologies for the representation and reasoning of the provenance of the data and provides a unifying framework for securing provenance that can help to address the various criteria of your information systems. Illustrating key concepts and practical techniques, the book considers cloud computing technologies that can enhance the scalability of solutions. After reading this book you will be better prepared to keep up with the on-going development of the prototypes, products, tools, and standards for secure data management, secure Semantic Web, secure web services, and secure cloud computing.

The increasing abundance of large high-quality datasets, combined with significant technical advances over the last several decades have made machine learning into a major tool employed across a broad array of tasks including vision, language, finance, and security. However, success has been accompanied with important new challenges: many applications of machine learning are adversarial in nature. Some are adversarial because they are safety critical, such as autonomous driving. An adversary in these applications can be a malicious party aimed at causing congestion or accidents, or may even model unusual situations that expose vulnerabilities in the prediction engine. Other applications are adversarial because their task and/or the data they use are. For example, an important class of problems in security involves detection, such as malware, spam, and intrusion detection. The use of machine learning for detecting malicious entities creates an incentive among adversaries to evade detection by changing their behavior or the content of malicius objects they develop. The field of adversarial machine learning has emerged to study vulnerabilities of machine learning approaches in adversarial settings and to develop techniques to make learning robust to adversarial manipulation. This book provides a technical overview of this field. After reviewing machine learning concepts and approaches, as well as common use cases of these in adversarial settings, we present a general categorization of attacks on machine learning. We then address two major categories of attacks and associated defenses: decision-time attacks, in which an adversary changes the nature of instances seen by a learned model at the time of prediction in order to cause errors, and poisoning or training time attacks, in which the actual training dataset is maliciously modified. In our final chapter devoted to technical content, we discuss recent techniques for attacks on deep learning, as well as approaches for improving robustness of deep neural networks. We conclude with a discussion of several important issues in the area of adversarial learning that in our view warrant further research. Given the increasing interest in the area of adversarial machine learning, we hope this book provides readers with the tools necessary to successfully engage in research and practice of machine learning in adversarial settings.

This book constitutes the refereed proceedings of the 4th International Conference on Decision and Game Theory for Security, GameSec 2013, held in Fort Worth, TX, USA, in November 2013. The 15 revised full papers presented were carefully reviewed and selected from numerous submissions. The conference focuses on analytical models based on game, information, communication, optimization, decision, and control theories that are applied to diverse security topics. At the same time, the connection between theoretical models and real world security problems are emphasized to establish the important feedback loop between theory and practice. Observing the scarcity of venues for researchers who try to develop a deeper theoretical understanding of the underlying incentive and resource allocation issues in security, we believe that GameSec will fill an important void and serve as a distinguished forum of highest standards for years to come.

Analyzing and Securing Social Networks focuses on the two major technologies that have been developed for online social networks (OSNs): (i) data mining technologies for analyzing these networks and extracting useful information such as location, demographics, and sentiments of the participants of the network, and (ii) security and privacy technologies that ensure the privacy of the participants of the network as well as provide controlled access to the information posted and exchanged by the participants. The authors explore security and privacy issues for social media systems, analyze such systems, and discuss prototypes they have developed for social media systems whose data are represented using semantic web technologies. These experimental systems have been developed at The University of Texas at Dallas. The material in this book, together with the numerous references listed in each chapter, have been used for a graduate-level course at The University of Texas at Dallas on analyzing and securing social media. Several experimental systems developed by graduate students are also provided. The book is divided into nine main sections: (1) supporting technologies, (2) basics of analyzing and securing social networks, (3) the authors' design and implementation of various social network analytics tools, (4) privacy aspects of social networks, (5) access control and inference control for social networks, (6) experimental systems designed or developed by the authors on analyzing and securing social networks, (7) social media application systems developed by the authors, (8) secure social media systems developed by the authors, and (9) some of the authors' exploratory work and further directions.