Decentralized Machine Learning Intelligence > Topics > Cybersecurity Data Mining

Cybersecurity Data Mining


With the explosive growth of computer and network communications in our daily life, Cybersecurity is raised to discuss the methodology and strategy that we can use to protect our data and resources from threats to confidentiality, integrity, and availability, in particular to instil confidence in online trade, commerce, banking, telemedicine, e-governance, and a host of other applications. Data Mining (DM) is a promising and reliable counterpart of the traditional signature-based techniques for protecting servers and PCs from malicious software, endless spam, and other adversaries. However, designing DM approaches to fulfilling the exorbitant expectation of end users and keeping up with the advances of network infrastructure and hardware, is just a starting point of problem-solving for Cybersecurity. Cybersecurity problems are challenging for contemporary DM techniques because it involves huge amount of information usually presented as data streams, real-time response requirements to prevent fast-spreading threats, dynamic characteristics of data sources, severe sampling bias in the training data, and inequality of misclassification costs. In the field of Cybersecurity Data Mining, we developed earlier, NIDVS: A Network Intrusion Detection Visualization System and HMEB: A Hierarchical Core Vector Machines for Network Intrusion Detection.