Abstract
The increasing development of cryptocurrencies has brought cryptojacking as a new security threat in which attackers steal computing resources for cryptomining. The digitization of the supply chain is a potential major target for cryptojacking due to the large number of different infrastructures involved. These different infrastructures provide information sources that can be useful to detect cryptojacking, but with a wide variety of data formats and encodings. This paper describes the Semantic Data Aggregator (SDA), a normalization and aggregation system based on data modelling and low-latency processing of data streams that facilitates the integration of heterogeneous information sources. As a use case, the paper describes a Cryptomining Detection System (CDS) based on network traffic flows processed by a machine learning engine. The results show how the SDA is leveraged in this use case to obtain aggregated information that improves the performance of the CDS.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have