Telephone networks first appeared more than a hundred years ago, forming the oldest large scale network that has grown to touch over 7 billion people. Telephony is now merging many complex technologies and because numerous services enabled by these technologies can be monetized, telephony attracts a lot of fraud. However, there is little academic work on this topic, in part because of the complexity of such networks and their closed nature.
In the first part of this thesis, we aim to systematically explore fraud in telephony networks. We propose a taxonomy that differentiates the root causes, the vulnerabilities, the exploitation techniques, the fraud types and finally the way fraud benefits fraudsters. In the second part, we
study two fraud types that manipulate the wholesale market. We start with Over-The-Top bypass fraud and measure its impact on a small mobile operator with more than 15,000 test calls and a large-scale user study. Later, we look at the International Revenue Share Fraud ecosystem, by analyzing several online premium rate service providers. Using this analysis, we propose a set of ML features that can be used to detect IRSF. In the last part, we study a recent countermeasure against voice spam, which involves the use of a chatbot to interact with spammers. We try to understand the effectiveness of this chatbot, by analyzing its conversations with various types of spammers.
While presenting a broad view of telephony fraud, our work also reveals its complex nature and the key challenges in fighting fraud. We hope to stimulate research in this area, in particular, leveraging interdisciplinary approaches to study the diverse effects of telephony fraud.