Mind your wallet's privacy: Identifying bitcoin wallet apps and user's actions through network traffic analysis
| Autor: | Fabio Aiolli, Mauro Conti, Mirko Polato, Ankit Gangwal |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
IOS
Cryptocurrency Traffic analysis Computer science business.industry media_common.quotation_subject 020207 software engineering 02 engineering and technology Payment Encryption App store World Wide Web Android Bitcoin Machine learning 020204 information systems 0202 electrical engineering electronic engineering information engineering Android (operating system) business media_common |
| Zdroj: | SAC |
| Popis: | With the surge in popularity of cryptocurrencies, Bitcoin has emerged as one of the most promising means for remittance, payments, and trading. Supplemented by the convenience offered by the smartphones, an increasing number of users are adopting Bitcoin wallet apps for different purposes. In this paper, we focus on identifying user activities on smart-phone-based Bitcoin wallet apps that are commonly used for sending, receiving, and trading Bitcoin. To accomplish our goal, we performed network traffic analysis using machine learning techniques. Since we focus on apps of the same type/functionality, it makes our classification problem even more difficult compared to classifying apps tailored for discrete purposes. Moreover, our goal is to identify user activities even in the presence of encryption. In our experiments, we considered the worldwide most downloaded Bitcoin wallet apps on both Google Play Store and Apple's App Store. For collecting network traffic traces, we used only physical hardware and omitted any emulator to build our experiment scenario as close to the real environment as possible. We process the traffic traces in several phases before extracting the features that are utilized to train our supervised learning algorithms. We deal with the classification problem in multiple stages in a hierarchical fashion. We ran a thorough set of experiments to assess the performance of our system and attained nearly 95% accuracy in user activity identification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|