Determining Attributes of Encrypted Data Traffic using Feature Selection Method
Tasmi1, Herri Setiawan2, Deris Stiawan3, Husnawati4, Sasut Analar Valiata5
1Tasmi*, Department of Computer Science Engineering, Srivijaya University Indonesia.
2Herri Setiawan, Department of Computer Science Engineering, Srivijaya University Indonesia.
3Deris Stiawan, Department of Computer Science Engineering, Srivijaya University Indonesia.
4Husnawati, Department of Computer Science Engineering, Srivijaya University Indonesia.
5Sasut Analar Valiata, Department of Computer Science Engineering, Sriwijaya University Indonesia.
Manuscript received on September 11, 2019. | Revised Manuscript received on September 22, 2019. | Manuscript published on October 30, 2019. | PP: 3500-3504 | Volume-9 Issue-1, October 2019 | Retrieval Number: A2674109119/2019©BEIESP | DOI: 10.35940/ijeat.A2674.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Encrypted packages such as banking and e commerce are widely used in various fields because it is advantages in terms of data security. However, the problem occurs when checking attributes package to determine if it is a safe packet instead of malware. The purpose of this study is to get the best attributes using feature selection processes by ranking. The results of this study found that from the two best methods of IG and One R, in average IG better than One R. If based on the results of the response, the data produced for the estimated data of TLS V1.0 IG method has better accuracy compared to the One R method, on the contrary in TLS V1.2 One R data is better than IG.
Keywords: Feature Selection, Feature Ranking, Encrypted Traffic.