Big Data Sanitization and Cyber Situational Awareness: A Network Telescope Perspective

摘要: This paper addresses the problems of data sanitization and cyber situational awareness by analyzing 910 GB real Internet-scale traffic, which has been passively collected monitoring close to 16.5 million darknet IP from a /8 /13 network telescopes. First, offers novel probabilistic preprocessing model, aims at sanitizing prepare it for effective use in task threat intelligence generation. Such model engineered using distributed multithreaded approach, rendering operational highly on big data. Second, further contributes presenting an innovative approach infer large-scale orchestrated probing campaigns leveraging data, Internet awareness. The uniquely reduces dimensionality such utilizing its artifacts, instead processing actual raw is accomplished extracting time series formal methods rooted Fourier transform Kalman filtering. Thorough empirical evaluations indeed validate accuracy performance proposed techniques. We assert that orchestration inference are significant value, given their postulated applicable nature field measurements security era