Here we propose novel methods for the One-Class Classification task and examine their applicability. Essentially, these methods extend the training set – which contains only positive examples – with artificially generated counterexamples. After, a two-class classifier is used to separate them. In this paper following a description of the existing and the newly proposed methods some problematic ...

Many applications require the ability to identify data that is anomalous with respect to a target group of observations, in the sense of belonging to a new, previously unseen ‘attacker’ class. One possible approach to this kind of verification problem is one-class classification, learning a description of the target class concerned based solely on data from this class. However, if known non-tar...

Detection of fake accounts on social networks is a challenging process. The previous methods in identification of fake accounts have not considered the strength of the users’ communications, hence reducing their efficiency. In this work, we are going to present a detection method based on the users’ similarities considering the network communications of the users. In the first step, similarity ...

Active learning has been utilized as an efficient tool in building anomaly detection models by leveraging expert feedback. In active framework, a model queries samples to be labeled experts and re-trains the with data samples. It unburdens obtaining annotated datasets while improving performance. However, most of existing studies focus on helping identify many abnormal possible, which is sub-op...