Comment Spam Injection Made Easy

Social networks heavily rely on the concept of reputation. Some platforms implement formalized systems to express reputation, for example as a rating, but the concept is broader and very often the reputation of a user, the perceived quality of a product, the popularity of a TV show or any other subject of published information stems from a more informal collection of comments and recommendations. Thus, guaranteeing the authenticity of the published data has become very important, and various systems have been developed to deal with this problem. However, in this paper we are going to demonstrate that the most commonly adopted filtering techniques do not adequately protect the messaging platforms from the automated injection of comments. The adopted methodology is quite empirical, but nonetheless it allows to point out not only the existence of the vulnerability, but also to make some educated guess about the reasons behind the failure of the tested filters. In the conclusion, we trace a possible path leading to a more effective solution.