 |
 |
|
|
|
Today online video is growing and becoming increasingly popular on the Web. It is no secret that illegal content is now a one-click-away from everyone, including children and minors. Intelligent video analysis methods can help to automatically detect and isolate questionable content in media. Unfortunately, these methods are hugely costly, and affecting public privacy. In this paper, we present an illegal domain detection system on large-scale video traffic, VegaStar. Using metadata of over 5 million URLs of video, VegaStar: (i)provides lexical and behavior characteristics of video domain names, (ii)proposes a model to detect illegal video domains constructed by twelve feature sets, (iii)detects website domains hosting illegal video content even before the videos are being downloaded, and (iv) understand different CDNs and cloud providers that host content for a particular resource. We conduct extensive experimental analysis and the result shows that the proposed model can classify domains with accuracy approximately 90% by cross validation experiments on Random Tree. We argue that VegaStar represents an important development in the field of video traffic identification, and it can be significantly improve the efficiency of former methods.
|