Anomaly detection associated with communities
Abstract:
A system and method for detecting unauthorized access to a plurality of network assets is described. The system and method receive a network asset feed from a plurality of data sources and then generating at least one social graph with the network asset feed. User communities are identified with the social graph and user accounts are associated with user communities. Commonly accessed network assets are identified from a firewall log, a router log or the combination thereof. A derived community is identified based on the user accounts associated with commonly accessed network assets. The systems and methods monitor communications associated with the user community so that the communications correspond to the derived community, and then reports an anomalous communication when the user community communications do not correspond to the derived community.
Public/Granted literature
Information query
Patent Agency Ranking
0/0