Identificação de Algoritmos Criptográficos Utilizando Aprensizado de Máquina e Processamento Massivo (Cryptographic Algorithm Identification Using Machine Learning and Massive Processing)

Flávio Luis de Mello (flavioluis.mello@gmail.com)1, José Antonio Moreira Xexéo (xexeo@ime.eb.br)2


1Universidade Federal do Rio de Janeiro
2Instituto Militar de Engenharia

This paper appears in: Revista IEEE América Latina

Publication Date: Nov. 2016
Volume: 14,   Issue: 11 
ISSN: 1548-0992


Abstract:
This paper presents a study on encryption algorithms identification by means of machine learning techniques. Plain text files, written in seven different languages, were encoded by seven cryptographic algorithm under ECB mode. The resulting cryptograms were submitted to a transformation so that it was possible to create metadata files. These files provide information for six data mining algorithms in order to identify the cryptographic algorithm used for encryption. The identification performance was evaluated and the language influence at the procedure was analyzed. The overall experiment involves many cryptograms, a great quantity of metadata, a huge time consuming computation, and therefore, it was employed a high performance computer. The successful identification for each mining algorithm is greater than a probabilistic bid, and there are several scenarios where algorithm identification reaches almost full recognition.

Index Terms:
cryptographic algorithm identification, data mining, machine intelligence, parallel computing   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (574)]