跳到主要內容

臺灣博碩士論文加值系統

(44.210.237.158) 您好!臺灣時間:2022/09/25 22:14
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:劉政鋼
研究生(外文):Cheng-Kang Liu
論文名稱:使用人臉辨識強化VPN身份認證
論文名稱(外文):Improvement of VPN Authentication Using Facial Recognition Technology
指導教授:范國清范國清引用關係陳映濃陳映濃引用關係
指導教授(外文):Kuo-Chin FanYing-Nong Chen
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程學系在職專班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2014
畢業學年度:102
語文別:中文
論文頁數:54
中文關鍵詞:虛擬私有網路
外文關鍵詞:VPN
相關次數:
  • 被引用被引用:0
  • 點閱點閱:392
  • 評分評分:
  • 下載下載:115
  • 收藏至我的研究室書目清單書目收藏:0
SSL VPN 是一種虛擬私有網路,可以在瀏覽器上使用,所有的網路資料傳輸都透過安全且經過身份認證的加密通道來進行傳輸。藉由SSL通訊協定可以提供客戶端與伺服器端之間更安全網路連結。在一般情況下,使用SSL VPN可以透過確認 LDAP 伺服器中的用戶憑證與密碼即可,但如果是要存取機密資料或是有特殊權限的使用者才可使用的資源,那我們就應該使用更高安全的身份驗證方法。故在本論文中提出一個使用者在登入使用SSLVPN之前,基於更高安全的理由,必須通過加入人臉辨識的雙層認證模式的SSLVPN架構。
在本系統架構中,使用者必須先通過SSL Handshake和使用者憑證認證,通過第一層的認證之後,以人臉辨識作為第二層的認證方法。系統使用從使用者端取的臉部資訊及參數進行人臉辨識,通過臉部辨識之後才可准許登入系統。
在實驗的部分人臉辨識率達88.7%,非本人辨識率達77%。由實驗結果得知,本論文提出以人臉辨識來加強SSL VPN身份認證的方法可以有效補強SSL VPN身份確認的功能,以降低在網路上頂替冒用身份的疑慮。

SSL VPN (Secure Sockets Layer Virtual Private Network) is a form of VPN that can be used with a standard web browser via a secure and authenticated pathway by encrypting all network traffic. This protocol achieves a higher level of compatibility with client and server platforms and hence provides a more reliable connection. In general, SSL VPN access can be granted by a user certificate and password in a LDAP. In some particular applications, SSL VPN intends to access important resources that are restricted and not as a general access solution. The resources require much higher secure authentication. In this thesis, we propose a novel SSL VPN double authentication scheme. An advanced feature is proposed based on endpoint security to check a connecting computer to make sure it passes facial recognition rules before allowing a user to log in to SSL VPN.
In the proposed scheme, if the authentication successfully passes the SSL handshake process and certification, it is then passed the face recognition as the second layer authentication. The server requests the facial recognition parameters from the client for authentication. If the authentication is successful, the protocols go to the next stage or the protocols fail. The client can login to access the server if only all the protocols are successful.
In our experiments, the accurate rate is 88.7% on images of person himself, and 77% on images of person non-self. From the experimental results, it indicates that our proposed scheme is an advance feature of identification on login to SSL VPN to decrease identification spoofing on the internet.

中文摘要 i
英文摘要 ii
誌謝 iii
第一章 緒論 1
1.1研究動機與目的 1
1.2相關研究 5
1.2.1 IPsec VPN 5
1.2.2 SSL VPN 5
1.3系統架構 7
1.3.1 系統應用架構 7
1.4 論文架構 11
第二章 SSL VPN介紹 12
2.1 TLS/SSL通訊協定 12
2.2 TLS/SSL Handshake協定 13
2.3 Digital Certificate數位憑證 15
第三章 人臉辨識 19
3.1 人臉偵測 19
3.2 主軸成份分析 21
3.3 最近特徵線轉換Nearest Feature Line(NFL) 24
3.4 支援向量機分類器Support Vector Machine(SVM) 26
第四章 實驗結果與討論 29
4.1 憑證認證 29
4.2 人臉辨識 31
4.3 實驗結果討論 34
第五章 結論和未來工作 39
5.1 結論 39
5.2 未來工作 41
參考文獻 42

[1] S. Kent and R. Atkinson, “Security Architecture for the Internet Proto- col”. RFC 2401, Nov. 1998.
[2] wiki. Secure Electronic Transaction. 2014年,取自http://en.wikipedi- a.org/wiki/Secure_Electronic_Transaction/.
[3] A. Frier, P. Karlton and P. Kocher, “The SSL 3.0 Protocol “, Netscape Communication Corporation, Nov. 1996.
[4] T. Dierks and C. Allen, “The TLS Protocol Version 1.0”, RFC2246, Jan. 1999.
[5] L.I. Smith, “A tutorial on principal components analysis”, 2002.
[6] S. Z. Li and J. Lu. “Face recognition using the nearest feature line method”. IEEE Transactions on Neural Networks, 10:439–433, Mar 1999.
[7] S. Z. Li, K. L. Chan, and C. L. Wang. “Performance evaluation of the nearest feature line method in image classification and retrieval”.IEEE Transactions on Pattern Analysis and Machine Intelligence,22:1335– 1339, Nov 2000.
[8] Ying-Nong Chen. “Face recognition using nearest feature space embe- dding”. PhD thesis, National Central University, Jan 2011.
[9] K. Jonsson, J. Matas, J. Kittler and Y. Li, “Learning support vectors for face verification and recognition”, IEEE International Conference on Automatic Face and Gesture Recognition, pp.208–213, 2000.
[10] OpenCV Project, 2014年,取自http://www.opencv.org/.
[11] Li. Zhao, Wei. Qi, S. Z. Li, S. Q. Yang, and H. J. Zhang. “Content- based retrieval of video shot using the-improved nearest feature line method”. Chinese Journal of Software, 13(4):586–590, April 2002.
[12] Ying-Nong Chen, Chin-Chuan Han, Cheng-Tzu Wang, and Kuo- Chin Fan. “Face recognition using nearest feature space embedding”.IEEE Transactions on Pattern Analysis and Machine Intelligence,33: 1073–1086, June 2011.
[13] J. Huang, P.C. Yuen, W.S. Chen and J.H. Lai, “Component-based subspace linear discriminant analysis method for face recognition with one training sample”, Optical Engineering, vol. 44, no. 5, May 2005.
[14] I. Rish, “An Empirical Study of The Naive Bayes Classifier”,Empiri- cal Methods in Artificial Intelligence, 2001.
[15] K.C.Fukushima,“A Self-Organizing Multilayered Neural Network”, Biological Cybernetics, vol.20, pp.121–136, 1975.
[16] L.E.Baum and T.Petrie,“Statistical Inference for Probabilistic Functio- ns of Finite State Markov Chains”, Ann. Math. Stat., vol. 37,pp.155 4–1563, 1966.
[17] J. Yang, D. Zhang, J.Y. Yang and B. Niu, “Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 4, pp. 650-664, Apr. 2007.
[18] Paul Viola Michael J. Jones, “Robust Real-Time Face Detection”, Int-.
ernational Journal of Computer Vision, Vol 57,pp.137-154,May 2004.
[19] 內政部憑證管理中心,2014年,取自http://moica.nat.gov.tw/.
[20] 李亭緯,「利用人臉五官為特徵之人臉辨識系統」,國立中央大學資訊工程研究所,碩士論文,民國97年。
[21] 涂麗玉,「利用模糊最近特徵線轉換做人臉辨識」,國立中央大學資訊工程研究所,碩士論文,民國103年。

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top