ABSTRACT
This conclusion presents some closing thoughts on the concepts covered in part 3 of this book. The part discusses security and privacy aware data science. Some of the directions include the following. In the case of adversarial support vector machine learning, a future direction for this work is to add cost-sensitive metrics into the learning models. Another direction is to extend the single learning model to an ensemble in which each base learner handles a different set of attacks. In the case of privacy preserving data mining, a future direction is to build the classifiers which can be used to classify the perturbed data set. In the case of privacy-aware policy-based data management framework, the next step is to carry out a detailed design and implementation of the framework. The part also discusses the various frameworks being proposed by organizations such as the American Civil Liberties Union.
