Detection of cyber threats to network infrastructure of digital production based on the methods of Big Data and multifractal analysis of traffica

• Main Authors: Lavrova Daria, Poltavtseva Maria, Shtyrkina Anna, Zegzhda Pyotr
• Format: Article
• Language: English
• Published: EDP Sciences 2018-01-01
• Series: SHS Web of Conferences
• Online Access: https://doi.org/10.1051/shsconf/20184400051

The article offers an approach to analyzing data security of network infrastructure of digital production providing for contraction of network traffic size and detecting anomalies in the network traffic on the basis of multifractal analysis. The contraction of data size will be provided due to extraction of significant parameters from the network packets and dropping the rest data, as well as due to application of such Big Data method as aggregation. The experimental investigations on contracting data size on analyzing security have proven the operability and efficiency thereof. The method of contracting data size has demonstrated a possibility of traffic volume contraction from hundreds of Gbit to several Mbyte. The suggested approach to security analysis using the assessment of width of multifractional spectrum as a criterion of anomaly presence has detected both simulated attacks of denial of servicing SYN-flood and smurf. Thus, the suggested approach can be efficiently used for analyzing big volumes of dissimilar traffic of network infrastructure of digital production.