Classification of encryption algorithms using Fisher's discriminant analysis
Defence Science Journal
Fisher's discriminant analysis (FDA) is a method used in statistics and machine learning which can often lead to good classification between several populations by maximising the separation between the populations. There is, literally, a huge body of literature which deals with the application of Fisher's discriminant analysis in problems of statistical classification and describes its desirable properties. The method is supposed to work well whenever there is a suitable numerical feature vector having different statistical distributions under the different classes. In this paper we will present some applications of FDA that discriminate between cipher texts in terms of a finite set of encryption algorithms. Specifically, we use ten algorithms, five each of stream and block cipher types, and, given a cipher text, try to identify which algorithm was used in the encryption of the given cipher. Our results display good classification with some of the features. Our limited study clearly shows that further exploration of this classification problem based on FDA could be worthwhile.
Ray, Prabhat Kumar; Kant, Shri; Roy, Bimal K.; and Basu, Ayanendranath, "Classification of encryption algorithms using Fisher's discriminant analysis" (2017). Journal Articles. 2795.