abstract: Data breaches have been on a rise and financial sector is among the top targeted. It can take a few months and upto a few years to identify the occurrence of a data breach. A major motivation behind data breaches is financial gain, hence most of the data ends up being on sale on the darkweb websites. It is important to identify sale of such stolen information on a timely and relevant manner. In this research, we present a system for timely identification of sale of stolen data on darkweb websites. We frame identifying sale of stolen data as a multi-label classification problem and leverage several machine learning approaches based on the thread content (textual) and social network analysis of the user communication seen on darkweb websites. The system generates alerts about trends based on popularity amongst the users of such websites. We evaluate our system using the K-fold cross validation as well as manual evaluation of blind (unseen) data. The method of combining social network and textual features outperforms baseline method i.e only using textual features, by 15 to 20 % improved precision. The alerts provide a good insight and we illustrate our findings by cases studies of the results. / Dissertation/Thesis / Masters Thesis Computer Science 2018

IT experts often struggle to find strategies to secure data on the cloud. Although current security standards might provide cloud compliance, they fail to offer guarantees of security assurance. The purpose of this qualitative case study was to explore the strategies used by IT security managers to host sensitive information in the commercial cloud. The study's population consisted of information security managers from a government agency in the eastern region of the United States. The routine active theory, developed by Cohen and Felson, was used as the conceptual framework for the study. The data collection process included IT security manager interviews (n = 7), organizational documents and procedures (n = 14), and direct observation of a training meeting (n = 35). Data collection from organizational data and observational data were summarized. Coding from the interviews and member checking were triangulated with organizational documents and observational data/field notes to produce major and minor themes. Through methodological triangulation, 5 major themes emerged from the data analysis: avoiding social engineering vulnerabilities, avoiding weak encryption, maintaining customer trust, training to create a cloud security culture, and developing sufficient policies. The findings of this study may benefit information security managers by enhancing their information security practices to better protect their organization's information that is stored in the commercial cloud. Improved information security practices may contribute to social change by providing by proving customers a lesser amount of risk of having their identity or data stolen from internal and external thieves