臺灣博碩士論文加值系統

洋蔥路由器(Tor）是以匿名通訊的方式在網路上進行，使用者利用Tor在網路上進行匿名交流，且不受地域限制。除此之外，利用Tor到達的網路空間是自然搜索所無法到達。但是為了保護使用者隱私而犧牲的傳輸時間，由多層資料加密解密和節點路徑選擇所佔據，使用者無法適當地選擇的當下對應的加密強度，使得機密隱私和無關重要的行為都是同樣的加密強度。本研究探討了洋蔥路由的加解密傳輸流程，提出一種不同加密強度的洋蔥路由，再利用機器學習對網址分類進行預測，提前分類別給予合適的傳輸加密強度。並且藉由自己提供節點來解決出口節點竊聽的問題，同時更彈性取有效的運用時間。

Wireless communication technology is fully developed, due to the rapid spread of tablet computers, smartphones, and other mobile information devices, together with the promotion and construction of telecommunication. Mobile Internet access has been a daily life for the general public. The Onion Router, better known as Tor, is a technique for anonymous communication over internet without regional restrictions. Apart from this, Tor can reach sites that normal search engine can’t search. Basically, the name of Tor is derived from its operation principle. Before original data reaching server, it has been encrypted layer by layer, just like onion. Our research proposed a system by using machine learning technique on URL in order to predict its category before visiting. According to the prediction, we serve three kinds of RSA key lengths on onion routing to represent different privacy level. Depending on various situations, it obtains the balance in security and in time cost. Giving flexibility to onion routing and make more good use of time.

摘要 I
ABSTRACT II
誌謝 XI
目錄 XII
表目錄 XIV
圖目錄 XV
第 一 章 緒論 1
1.1研究背景 1
1.2研究動機及目的 2
1.3研究貢獻 3
1.4章節規劃 3

第 二 章 研究背景與文獻探討 4
2.1洋蔥網路 4
2.1.1為什麼需要Tor 5
2.1.2 組成員件 6
2.1.3 洋蔥協定 7
2.2 THE SHADOW SIMULATOR 9
2.3 網頁分類 10

第 三 章 系統架構 13
3.1 環境假設 13
3.2 系統架構 14
3.2.1 彈性加密洋蔥路由 15
3.2.2 開放目錄專案 20
3.2.3 分類器 22
3.2.4 特徵選取 26
 
第 四 章 實驗效能評估 29
4.1 開發環境 29
4.2 效能分析 30
4.2.1 時間效能比較 30
4.2.2 評估指標 31
4.2.3 準確率比較 32

第 五 章 結論與未來工作 40
5.1 結論 40
5.2 未來工作 41

參考文獻 42

[1]“The onion router(Tor) [Online]. Available: https://www.torproject.org/. [Accessed 2018/07/1].
[2]“Tor metrics [Online]. Available: https://metrics.torproject.org/. [Accessed 2018/07/1].
[3]Jansen, R., ＆ Hooper, N. (2011). Shadow: Running Tor in a box for accurate and efficient experimentation (No. TR-11-020). MINNESOTA UNIV MINNEAPOLIS DEPT OF COMPUTER SCIENCE AND ENGINEERING.
[4]Wardana, H. K., Handianto, L. F., ＆ Yohanes, B. W. (2017, September). The onion routing performance using shadow-plugin-TOR. In Electrical Engineering, Computer Science and Informatics (EECSI), 2017 4th International Conference on (pp. 1-5). IEEE.
[5]“dmoz [Online]. Available: http://dmoz-odp.org/. [Accessed 2018/07/1].
[6]“VirusTotal [Online]. Available: https://www.virustotal.com/zh-tw/. [Accessed 2018/07/1].
[7]Qi, X., ＆ Davison, B. D. (2009). Web page classification: Features and algorithms. ACM computing surveys (CSUR), 41(2), 12.
[8]Lim, C. S., Lee, K. J., ＆ Kim, G. C. (2005). Multiple sets of features for automatic genre classification of web documents. Information processing ＆ management, 41(5), 1263-1276.
[9]Zhang, J., Qin, J., ＆ Yan, Q. (2006, December). The role of URLs in objectionable web content categorization. In Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence (pp. 277-283). IEEE Computer Society.
[10]Wikipedia, RSA (cryptosystem) [Online]. Available: https://en.wikipedia.org/wiki/RSA_(cryptosystem). [Accessed 2018/07/1].
[11]Wikipedia, Advanced Encryption Standard [Online]. Available: https://en.wikipedia.org/wiki/Advanced_Encryption_Standard. [Accessed 2018/07/1].
[12]Hsu, C. W., Chang, C. C., ＆ Lin, C. J. (2003). A practical guide to support vector classification.
[13]Rish, I. (2001, August). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46). New York: IBM.
[14]Brown, P. F., Desouza, P. V., Mercer, R. L., Pietra, V. J. D., ＆ Lai, J. C. (1992). Class-based n-gram models of natural language. Computational linguistics, 18(4), 467-479.
[15]Cavnar, W. B. (1993). N-gram-based text filtering for TREC-2. Ann Arbor, 1001, 48113-4001.
[16]Kimbrell, R. E. (1988). Searching for text? Send an n-gram. Byte, 13(5), 297-312.
[17]Suen, C. Y. (1979). N-gram statistics for natural language understanding and text processing. IEEE transactions on pattern analysis and machine intelligence, (2), 164-172.
[18]Guyon, I., ＆ Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3(Mar), 1157-1182.
[19]Biesiada, J., ＆ Duch, W. (2007). Feature selection for high-dimensional data—a Pearson redundancy based filter. In Computer recognition systems 2 (pp. 242-249). Springer, Berlin, Heidelberg.
[20]Kan, M. Y., ＆ Thi, H. O. N. (2005, October). Fast webpage classification using URL features. In Proceedings of the 14th ACM international conference on Information and knowledge management (pp. 325-326). ACM.
[21]Baykan, E., Henzinger, M., Marian, L., ＆ Weber, I. (2009, April). Purely URL-based topic classification. In Proceedings of the 18th international conference on World wide web (pp. 1109-1110). ACM.
[22]Rajalakshmi, R., and C. Aravindan. Naive bayes approach for website classification. Information Technology and Mobile Communication. Springer, Berlin, Heidelberg, 2011. 323-326.
[23]Rajalakshmi, R., ＆ Aravindan, C. (2013, December). Web page classification using n-gram based URL features. In Advanced Computing (ICoAC), 2013 Fifth International Conference on (pp. 15-21). IEEE.