摘要：Pseudo base station (PBS), sometimes called fake base station, refers to cellular base stations that are employed for malicious and usually illegal purposes. Through the pitfalls of the GSM protocol, PSBs can hijack GSM signals of cellphones close by. Most PBSes are portable, for example hidden in vans or even carried in backpacks, and are deployed in densely populated regions. Then they can steal personal information from neighboring smartphones, or send intriguing messages to them that would ultimately lead to telecom frauds. In recent years, there has been a terrifying increase in the number of telecom frauds and the smartphones infected by viruses sent from PBSes. This urgently calls for methods and systems that can effectively identify and track PBSes. In this study, we designed and implemented a PBS detecting and tracking system, by conducting topic analysis of messages received by cellphones and analyzing their temporal and spatial distribution patterns. Using the system, we could perform a variety of exploratory analysis, including categorizing PBSes into either stationary or moving PBSes, discovering and visualizing their behavior patterns, and identifying districts that tend to suffer from a particular type of fraud messages.
关键词：Pseudo Base Station; telecom fraud; topic modeling; trajectory clustering; visualization
