Identifying Top Sellers In Underground Economy Using Deep Learning-Based Sentiment Analysis

This paper presents a deep learning-based framework for identifying top malware/carding sellers that uses snowball sampling, thread classification, and deepLearning-based sentiment analysis to evaluate sellers' product/service quality based on customer feedback.

Abstract

The underground economy is a key component in cyber carding crime ecosystems because it provides a black marketplace for cyber criminals to exchange malicious tools and services that facilitate all stages of cyber carding crime. Consequently, black market sellers are of particular interest to cybersecurity researchers and practitioners. Malware/carding sellers are critical to cyber carding crime since using malwares to skim credit/debit card information and selling stolen information are two major steps of conducting such crime. In the underground economy, the malicious product/service quality is reflected by customers' feedback. In this paper, we present a deep learning-based framework for identifying top malware/carding sellers. The framework uses snowball sampling, thread classification, and deep learning-based sentiment analysis to evaluate sellers' product/service quality based on customer feedback. The framework was evaluated on a Russian carding forum and top malware/carding sellers from it were identified. Our framework contributes to underground economy research as it provides a scalable and generalizable framework for identifying key cybercrime facilitators.