Identifica??o remota de sistemas operacionais utilizando an?lise de processos aleat?rios e redes neurais artificiais

Made available in DSpace on 2014-12-17T14:55:36Z (GMT). No. of bitstreams: 1 JoaoPSM.pdf: 2736653 bytes, checksum: 0b1bd7853a47877b24c5f2042e0a5d8e (MD5) Previous issue date: 2009-06-19 === Petr?leo Brasileiro SA - PETROBRAS === A new method to perform TCP/IP fingerprinting is proposed. TCP/IP fin...

Full description

Bibliographic Details
Main Author: Medeiros, Jo?o Paulo de Souza
Other Authors: CPF:87830574472
Format: Others
Language:Portuguese
Published: Universidade Federal do Rio Grande do Norte 2014
Subjects:
Online Access:http://repositorio.ufrn.br:8080/jspui/handle/123456789/15287
Description
Summary:Made available in DSpace on 2014-12-17T14:55:36Z (GMT). No. of bitstreams: 1 JoaoPSM.pdf: 2736653 bytes, checksum: 0b1bd7853a47877b24c5f2042e0a5d8e (MD5) Previous issue date: 2009-06-19 === Petr?leo Brasileiro SA - PETROBRAS === A new method to perform TCP/IP fingerprinting is proposed. TCP/IP fingerprinting is the process of identify a remote machine through a TCP/IP based computer network. This method has many applications related to network security. Both intrusion and defence procedures may use this process to achieve their objectives. There are many known methods that perform this process in favorable conditions. However, nowadays there are many adversities that reduce the identification performance. This work aims the creation of a new OS fingerprinting tool that bypass these actual problems. The proposed method is based on the use of attractors reconstruction and neural networks to characterize and classify pseudo-random numbers generators === ? proposto um novo m?todo para identifica??o remota de sistemas operacionais que operam em redes TCP/IP. Este m?todo possui diversas aplica??es relacionadas ? seguran?a em redes de computadores e ? normalmente adotado tanto em atividades de ataque quanto de defesa de sistemas. O m?todo proposto ? capaz de obter sucesso em situa??es onde diversas solu??es atuais falham, inclusive no tratamento com dispositivos possivelmente vulner?veis ao processo de identifica??o. O novo m?todo realiza a an?lise dos geradores de n?meros aleat?rios usados nas pilhas TCP/IP e, atrav?s do uso de redes neurais artificiais, cria mapas que representam o comportamento destes geradores. Tais mapas s?o usados para compara??o com mapas rotulados que representam sistemas j? conhecidos, concretizando o processo de identifica??o