本文選題：網(wǎng)絡(luò)釣魚 + 特征提取��； 參考：《電子科技大學(xué)》2017年碩士論文

【摘要】：大數(shù)據(jù)時(shí)代,網(wǎng)絡(luò)安全仍是舉足輕重的話題。在海量信息中,不乏非法分子利用網(wǎng)絡(luò)騙取用戶信任并從中獲利,釣魚網(wǎng)站就是其中之一。“釣魚”網(wǎng)站的網(wǎng)址、網(wǎng)頁內(nèi)容、布局等與真實(shí)網(wǎng)站極其相似,沒有安全意識(shí)的網(wǎng)民容易因此上當(dāng)受騙,造成嚴(yán)重后果。有效遏制“釣魚網(wǎng)站”是網(wǎng)絡(luò)安全的保障。目前,國內(nèi)外在防御釣魚網(wǎng)站的研究上各有建樹,然而都存在缺陷�，F(xiàn)有的比較典型的檢測(cè)釣魚網(wǎng)站的方法有:基于黑白名單機(jī)制的檢測(cè)、基于文本特征或網(wǎng)頁圖像特征的匹配檢測(cè)、基于機(jī)器學(xué)習(xí)的分類檢測(cè)。然而,基于黑白名單的檢測(cè)方法時(shí)效性較差、名單范圍也存在著不足,基于特征的算法的準(zhǔn)確性和魯棒性又不是很理想。近年來,機(jī)器學(xué)習(xí)應(yīng)用于各領(lǐng)域并取得巨大成功,尤其是將深度學(xué)習(xí)應(yīng)用于檢測(cè)識(shí)別可以有效得提高檢測(cè)效率。鑒于以上,本文研究已有的技術(shù)方法,提出基于深度學(xué)習(xí)的、具有魯棒性的釣魚網(wǎng)站檢測(cè)方法。基于深度學(xué)習(xí)的釣魚網(wǎng)站檢測(cè)主要研究以下內(nèi)容:釣魚網(wǎng)站的特征提取是識(shí)別釣魚網(wǎng)站的基礎(chǔ)也是關(guān)鍵的一步,一個(gè)好的特征提取方法對(duì)檢測(cè)結(jié)果起著至關(guān)重要的作用。通過對(duì)釣魚網(wǎng)站特征的調(diào)研,以及對(duì)前人研究的總結(jié),本文把網(wǎng)站頁面和網(wǎng)頁網(wǎng)址相結(jié)合,分別提取關(guān)于網(wǎng)頁內(nèi)容異常和鏈接異常的關(guān)鍵特征。為了提高檢測(cè)速度和減少誤判率采用了URL過濾器,并對(duì)爬取的URL進(jìn)行相似度檢測(cè)進(jìn)一步提高檢測(cè)的準(zhǔn)確性,將網(wǎng)址特征和網(wǎng)頁特征進(jìn)行預(yù)處理并保存成特征向量以待下一模塊的檢測(cè)識(shí)別。近幾年深度學(xué)習(xí)技術(shù)的提出以及其出色的特征學(xué)習(xí)能力使其在各領(lǐng)域的應(yīng)用中取得巨大成功。因此,本文研究基于深度學(xué)習(xí)的釣魚網(wǎng)站分類識(shí)別方法,并提出多層結(jié)構(gòu)的DBN-KNN模型,將其運(yùn)用到釣魚網(wǎng)站特征的識(shí)別中,再對(duì)上述提取的特征向量進(jìn)行學(xué)習(xí)、訓(xùn)練和分類,最后根據(jù)分類結(jié)果判別出釣魚網(wǎng)站。綜上,本學(xué)術(shù)論文針對(duì)現(xiàn)有檢測(cè)方法的缺陷,研究基于深度學(xué)習(xí)的釣魚網(wǎng)站檢測(cè)方法。首先,爬取釣魚網(wǎng)站數(shù)據(jù)并進(jìn)行URL過濾和相似度檢測(cè);然后,人工分析并提取釣魚網(wǎng)站的關(guān)鍵特征再對(duì)特征進(jìn)行預(yù)處理;最后,提出深度學(xué)習(xí)模型DBN-KNN對(duì)特性向量進(jìn)行訓(xùn)練分類,識(shí)別出釣魚網(wǎng)站。
[Abstract]:In the era of big data, network security is still an important topic. Among the vast amount of information, there are many illegal elements who use the network to deceive users to trust and profit from it, among which phishing websites are one of them. "fishing" website URL, page content, layout and so on are very similar to the real site, no security awareness of the Internet users are easy to be deceived, resulting in serious consequences. Effective containment of "phishing website" is the guarantee of network security. At present, domestic and foreign research in the defense of fishing sites have their own achievements, but there are shortcomings. There are several typical methods to detect phishing websites: black-and-white list based detection, text feature or page image feature matching detection, machine learning based classification detection. However, the method based on black-and-white list is of poor timeliness, and the scope of the list is also inadequate. The accuracy and robustness of the feature-based algorithm are not ideal. In recent years, machine learning has been applied to various fields with great success, especially the application of depth learning in detection and recognition can effectively improve the detection efficiency. In view of the above, this paper studies the existing technical methods, and proposes a robust fishing site detection method based on depth learning. The research of phishing website detection based on deep learning is as follows: feature extraction of phishing website is the basis and key step to identify phishing website. A good feature extraction method plays an important role in the detection results. By investigating the features of phishing websites and summarizing the previous studies, this paper combines the web pages and web addresses to extract the key features of abnormal page content and link anomalies respectively. In order to improve the detection speed and reduce the error rate, the URL filter is adopted, and the similarity detection of crawling URL is carried out to further improve the accuracy of the detection. The URL features and web page features are preprocessed and stored as feature vectors to be detected and identified by the next module. In recent years, with the development of deep learning technology and its excellent feature learning ability, it has achieved great success in various fields. Therefore, this paper studies the classification and recognition method of phishing websites based on deep learning, and puts forward a multi-layer structure DBN-KNN model, which is applied to the recognition of phishing site features, and then studies, trains and classifies the extracted feature vectors. Finally, the fishing site is identified according to the classification results. In summary, aiming at the defects of existing detection methods, this paper studies the detection method of phishing website based on deep learning. First of all, crawl the fishing site data and carry out URL filtering and similarity detection; then manually analyze and extract the key features of the fishing site and preprocess the features; finally, the depth learning model DBN-KNN is proposed to train and classify the feature vector. Identify fishing sites.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP393.092

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 鐘沖;徐光柱;;結(jié)合前景檢測(cè)和深度學(xué)習(xí)的運(yùn)動(dòng)行人檢測(cè)方法[J];計(jì)算機(jī)與數(shù)字工程;2016年12期

2 李婉華;陳宏;郭昆;郭松榮;韓嘉民;陳羽中;;基于隨機(jī)森林算法的用電負(fù)荷預(yù)測(cè)研究[J];計(jì)算機(jī)工程與應(yīng)用;2016年23期

3 曾傳璜;李思強(qiáng);張小紅;;基于AdaCostBoost算法的網(wǎng)絡(luò)釣魚檢測(cè)[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2015年09期

4 姜華;韓安琪;王美佳;王崢;吳栻玲;;基于改進(jìn)編輯距離的字符串相似度求解算法[J];計(jì)算機(jī)工程;2014年01期

5 王婷;彭勇;戴忠華;伊勝偉;韓蘭勝;;基于SVM-RFE的釣魚網(wǎng)頁檢測(cè)方法研究[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年S2期

6 ;2012中國反釣魚網(wǎng)站聯(lián)盟年會(huì)在京召開[J];信息安全與通信保密;2012年12期

7 張玉芳;艾東梅;黃濤;熊忠陽;;結(jié)合編輯距離和Google距離的語義標(biāo)注方法[J];計(jì)算機(jī)應(yīng)用研究;2010年02期

8 曹玖新;毛波;羅軍舟;劉波;;基于嵌套EMD的釣魚網(wǎng)頁檢測(cè)算法[J];計(jì)算機(jī)學(xué)報(bào);2009年05期

相關(guān)博士學(xué)位論文 前1條

1 閆琰;基于深度學(xué)習(xí)的文本表示與分類方法研究[D];北京科技大學(xué);2016年

相關(guān)碩士學(xué)位論文 前4條

1 趙加林;基于K-Means和SVM的釣魚網(wǎng)站識(shí)別的研究[D];西南交通大學(xué);2016年

2 白雪;基于DBN的網(wǎng)絡(luò)流量分類的研究[D];內(nèi)蒙古大學(xué);2015年

3 沈尚方;釣魚網(wǎng)頁的深度學(xué)習(xí)智能檢測(cè)方法研究[D];華北電力大學(xué);2012年

4 趙留軍;一種基于TSVM的phishing網(wǎng)頁檢測(cè)方法[D];華北電力大學(xué)（北京）;2011年

，

本文編號(hào)：1991064