Data Science in Cyber-Security and Related Statistical Challenges

Опубликовано 4 сентября 2018, 18:01

Data science techniques have an important role to play in the next generation of cyber-security defenses. Inside a typical enterprise computer network, a number of high-volume data sources are available which could enable the discovery and prevention of cyber-attacks and any other nefarious network activity. At Imperial, our interests are in developing statistical, probability model-based techniques for identifying subtle intrusion attempts using these data sources. This talk will present two examples in anomaly detection, analyzing authentication logs and network flow records. Relatively simple statistical models will be considered in both cases; the methodological focus will be placed on combining weak signals and reducing false positive detections in changepoint analysis.

See more at microsoft.com/en-us/research/v...