在線社交網(wǎng)絡(luò)惡意網(wǎng)址檢測
發(fā)布時(shí)間：2018-09-17 17:46
【摘要】：在線社交網(wǎng)絡(luò)已經(jīng)成為人們熟悉的交流平臺(tái),例如Facebook、Twitter、以及新浪微博等。與此同時(shí),其開放性也引起了攻擊者的關(guān)注。攻擊者嘗試?yán)蒙缃痪W(wǎng)絡(luò)平臺(tái)傳播和隱藏包含惡意網(wǎng)址的消息,間接對用戶隱私安全構(gòu)成威脅。為了解決在線社交網(wǎng)絡(luò)上存在的惡意網(wǎng)址問題,研究學(xué)者、安全機(jī)構(gòu)不斷提出了對應(yīng)的解決方案;主要包括消息中惡意網(wǎng)址檢測以及spammer檢測兩個(gè)方向。當(dāng)前大部分檢測社交消息中惡意網(wǎng)址的解決方法是采用機(jī)器學(xué)習(xí)策略。此類方法會(huì)基于不同種類的特征集合,訓(xùn)練并構(gòu)建檢測器。不過,大部分現(xiàn)有工作中采取的特征主要是基于常規(guī)消息、以及賬戶特征等,與社交網(wǎng)絡(luò)平臺(tái)的特性并不相關(guān)。對于spammer檢測,現(xiàn)有工作主要是針對社交網(wǎng)絡(luò)中單一用戶節(jié)點(diǎn)進(jìn)行檢測,而且,部分算法過度依賴于用戶之間的社交網(wǎng)絡(luò)關(guān)系。此類檢測方法多會(huì)造成對同一用戶的重復(fù)檢測,并且不能有效的、一次性地清除采取策略潛藏的spammer團(tuán)體。因此,有必要通過消息傳播路徑,將spammer與其發(fā)送的消息統(tǒng)一起來共同考慮。同時(shí),利用消息相關(guān)聯(lián)的用戶的可疑程度,也能夠在有限次數(shù)內(nèi)將潛藏的spammer團(tuán)體有效清除。本文針對社交消息中惡意網(wǎng)址檢測方向,提出了基于消息轉(zhuǎn)發(fā)的特征集合,并依此類特征設(shè)計(jì)了惡意網(wǎng)址檢測器。轉(zhuǎn)發(fā)行為是消息傳播的主要途徑,能夠促進(jìn)消息在社交網(wǎng)絡(luò)平臺(tái)上實(shí)時(shí)、快速的傳播。為了驗(yàn)證檢測器的性能,我們收集了大約有100 000條初始新浪微博消息,作為轉(zhuǎn)發(fā)行為分析與研究的數(shù)據(jù)樣本。經(jīng)過訓(xùn)練以及檢測器性能測試,該分類器的準(zhǔn)確率為83.21%,而誤報(bào)率為10.3%。為了驗(yàn)證提出的轉(zhuǎn)發(fā)特征集的有效性,通過構(gòu)建不包含此類特征的檢測器,并與先前所設(shè)計(jì)檢測器進(jìn)行對比實(shí)驗(yàn),其結(jié)果充分說明了基于消息轉(zhuǎn)發(fā)行為特征在社交網(wǎng)絡(luò)惡意網(wǎng)址檢測研究上的有效性。針對spammer檢測方向,本文引入了消息轉(zhuǎn)發(fā)樹,通過消息傳播路徑,將賬戶與其發(fā)送的消息統(tǒng)一結(jié)合起來。采用此方法,有利于解決社交網(wǎng)絡(luò)中采用策略進(jìn)行潛藏的spammer團(tuán)體問題。首先,分析并總結(jié)了基于消息轉(zhuǎn)發(fā)樹的6個(gè)特征,分別是消息轉(zhuǎn)發(fā)樹層級(jí)、傳播范圍、重復(fù)轉(zhuǎn)發(fā)行為、傳播速度、以及消息轉(zhuǎn)發(fā)樹的權(quán)值均值。其次,通過機(jī)器學(xué)習(xí)策略,對此類特征集合矩陣進(jìn)行訓(xùn)練并生成檢測器。實(shí)驗(yàn)結(jié)果表明,該檢測器的準(zhǔn)確率高達(dá)95.3%,而誤報(bào)率僅為0.5%。最后,對參與訓(xùn)練的特征集合進(jìn)行特征影響度排名,結(jié)果表明基于消息轉(zhuǎn)發(fā)樹的特征都位居前列。同時(shí),提出并采用了基于轉(zhuǎn)發(fā)特征以及消息轉(zhuǎn)發(fā)樹的概念,在此領(lǐng)域尚屬首例,對同類工作有借鑒意義。
[Abstract]:Online social networks have become familiar communication platforms, such as Facebook,Twitter, and Sina Weibo. At the same time, its openness also attracted the attention of the attackers. An attacker attempts to spread and hide messages containing malicious web addresses on a social network platform, which indirectly threatens the privacy of users. In order to solve the problem of malicious web address in online social network, researchers and security organizations have put forward corresponding solutions, mainly including malicious URL detection and spammer detection. At present, most of the solutions to detect malicious web addresses in social messages are machine learning strategies. Such methods train and construct detectors based on different types of feature sets. However, most of the features taken in the current work are based on regular messages and account features, and are not related to the features of the social network platform. For spammer detection, the existing work mainly focuses on the detection of single user nodes in social networks, and some of the algorithms are overly dependent on the social network relationships between users. This kind of detection method often results in repeated detection of the same user, and it can not effectively eliminate the spammer group that has adopted the strategy in one time. Therefore, it is necessary to unify the spammer and the message it sends through the message propagation path. At the same time, using the suspicious degree of users associated with messages, the hidden spammer group can be effectively removed in a limited number of times. In this paper, a message forwarding based feature set is proposed to detect malicious web addresses in social messages, and a malicious URL detector is designed according to these features. Forwarding behavior is the main way to spread messages, which can promote the real-time and fast spread of messages on the social network platform. To verify the performance of the detector, we collected about 100,000 initial Sina Weibo messages as data samples for forwarding behavior analysis and research. After training and detector performance testing, the accuracy of the classifier is 83.21, and the false alarm rate is 10.3. In order to verify the validity of the proposed forwarding feature set, a detector that does not contain such features is constructed and compared with the previously designed detector. The results fully demonstrate the effectiveness of message forwarding behavior in the research of malicious web address detection in social networks. Aiming at the direction of spammer detection, this paper introduces a message forwarding tree, which unifies the account with the message it sends through the message propagation path. This method is helpful to solve the problem of spammer group which is hidden by strategy in social network. Firstly, six characteristics of message forwarding tree based on message forwarding tree are analyzed and summarized, which are message forwarding tree level, propagation range, repeat forwarding behavior, propagation speed and the average weight of message forwarding tree. Secondly, this kind of feature set matrix is trained by machine learning strategy and the detector is generated. The experimental results show that the accuracy of the detector is as high as 95.3 and the false alarm rate is only 0.5. Finally, we rank the feature sets involved in the training, and the results show that the features based on message forwarding tree are in the forefront. At the same time, the concepts based on forwarding feature and message forwarding tree are proposed and adopted, which is the first example in this field.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP393.08
[Abstract]:Online social networks have become familiar communication platforms, such as Facebook,Twitter, and Sina Weibo. At the same time, its openness also attracted the attention of the attackers. An attacker attempts to spread and hide messages containing malicious web addresses on a social network platform, which indirectly threatens the privacy of users. In order to solve the problem of malicious web address in online social network, researchers and security organizations have put forward corresponding solutions, mainly including malicious URL detection and spammer detection. At present, most of the solutions to detect malicious web addresses in social messages are machine learning strategies. Such methods train and construct detectors based on different types of feature sets. However, most of the features taken in the current work are based on regular messages and account features, and are not related to the features of the social network platform. For spammer detection, the existing work mainly focuses on the detection of single user nodes in social networks, and some of the algorithms are overly dependent on the social network relationships between users. This kind of detection method often results in repeated detection of the same user, and it can not effectively eliminate the spammer group that has adopted the strategy in one time. Therefore, it is necessary to unify the spammer and the message it sends through the message propagation path. At the same time, using the suspicious degree of users associated with messages, the hidden spammer group can be effectively removed in a limited number of times. In this paper, a message forwarding based feature set is proposed to detect malicious web addresses in social messages, and a malicious URL detector is designed according to these features. Forwarding behavior is the main way to spread messages, which can promote the real-time and fast spread of messages on the social network platform. To verify the performance of the detector, we collected about 100,000 initial Sina Weibo messages as data samples for forwarding behavior analysis and research. After training and detector performance testing, the accuracy of the classifier is 83.21, and the false alarm rate is 10.3. In order to verify the validity of the proposed forwarding feature set, a detector that does not contain such features is constructed and compared with the previously designed detector. The results fully demonstrate the effectiveness of message forwarding behavior in the research of malicious web address detection in social networks. Aiming at the direction of spammer detection, this paper introduces a message forwarding tree, which unifies the account with the message it sends through the message propagation path. This method is helpful to solve the problem of spammer group which is hidden by strategy in social network. Firstly, six characteristics of message forwarding tree based on message forwarding tree are analyzed and summarized, which are message forwarding tree level, propagation range, repeat forwarding behavior, propagation speed and the average weight of message forwarding tree. Secondly, this kind of feature set matrix is trained by machine learning strategy and the detector is generated. The experimental results show that the accuracy of the detector is as high as 95.3 and the false alarm rate is only 0.5. Finally, we rank the feature sets involved in the training, and the results show that the features based on message forwarding tree are in the forefront. At the same time, the concepts based on forwarding feature and message forwarding tree are proposed and adopted, which is the first example in this field.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP393.08
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 ;基于位置的手機(jī)社交網(wǎng)絡(luò)“貝多”正式發(fā)布[J];中國新通信;2008年06期
2 曹增輝;;社交網(wǎng)絡(luò)更偏向于用戶工具[J];信息網(wǎng)絡(luò);2009年11期
3 ;美國:印刷企業(yè)青睞社交網(wǎng)絡(luò)營銷新方式[J];中國包裝工業(yè);2010年Z1期
4 李智惠;柳承燁;;韓國移動(dòng)社交網(wǎng)絡(luò)服務(wù)的類型分析與促進(jìn)方案[J];現(xiàn)代傳播(中國傳媒大學(xué)學(xué)報(bào));2010年08期
5 賈富;;改變一切的社交網(wǎng)絡(luò)[J];互聯(lián)網(wǎng)天地;2011年04期
6 譚拯;;社交網(wǎng)絡(luò):連接與發(fā)現(xiàn)[J];廣東通信技術(shù);2011年07期
7 陳一舟;;社交網(wǎng)絡(luò)的發(fā)展趨勢[J];傳媒;2011年12期
8 殷樂;;全球社交網(wǎng)絡(luò)新態(tài)勢及文化影響[J];新聞與寫作;2012年01期
9 許麗;;社交網(wǎng)絡(luò):孤獨(dú)年代的集體狂歡[J];上海信息化;2012年09期
10 李玲麗;吳新年;;科研社交網(wǎng)絡(luò)的發(fā)展現(xiàn)狀及趨勢分析[J];圖書館學(xué)研究;2013年01期
相關(guān)會(huì)議論文 前10條
1 趙云龍;李艷兵;;社交網(wǎng)絡(luò)用戶的人格預(yù)測與關(guān)系強(qiáng)度研究[A];第七屆（2012）中國管理學(xué)年會(huì)商務(wù)智能分會(huì)場論文集（選編）[C];2012年
2 宮廣宇;李開軍;;對社交網(wǎng)絡(luò)中信息傳播的分析和思考——以人人網(wǎng)為例[A];首屆華中地區(qū)新聞與傳播學(xué)科研究生學(xué)術(shù)論壇獲獎(jiǎng)?wù)撐腫C];2010年
3 楊子鵬;喬麗娟;王夢思;楊雪迎;孟子冰;張禹;;社交網(wǎng)絡(luò)與大學(xué)生焦慮緩解[A];心理學(xué)與創(chuàng)新能力提升——第十六屆全國心理學(xué)學(xué)術(shù)會(huì)議論文集[C];2013年
4 畢雪梅;;體育虛擬社區(qū)中的體育社交網(wǎng)絡(luò)解析[A];第九屆全國體育科學(xué)大會(huì)論文摘要匯編(4)[C];2011年
5 杜p，
本文編號(hào)：2246659
本文鏈接：http://sikaile.net/guanlilunwen/ydhl/2246659.html
最近更新
教材專著
