SEC595: Applied Data Science and AI/Machine Learning for Cybersecurity Professionals

Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact UsAbstract: Accountants and tax filing businesses use complex software to automate the preparation and electronic filing of tax returns. Cybercriminals harvest identities, breach networks, and impersonate legitimate users to leverage tax software to defraud the government, the affected businesses, and citizens for over $1 billion annually (McTigue, 2018). The IRS and tax software companies have partnered to implement controls focused on authentication, authorization, and detection to identify fraudulent tax returns before they are processed. These controls successfully prevent upwards of $10 billion of fraudulent filing a year (McTigue, 2018), but those controls focus on an analysis of the 'who' and 'what' components of tax returns. This paper uses Geolocation tools to look at the 'where' component of tax returns by analyzing legitimate and fraudulent tax return electronic filing data to look for trends and patterns. The goal of this paper is to determine if Geolocation technologies can be used as an additional layer of controls to support a defense in depth approach of fraud prevention.