面向社會化推薦的托攻擊及檢測研究
發(fā)布時間：2019-03-26 09:21
【摘要】：隨著電子商務(wù)零售業(yè)的迅猛發(fā)展和社交網(wǎng)絡(luò)營銷的興起,以用戶間社交關(guān)系作為額外輸入的社會化推薦系統(tǒng)成為新的研究方向。社會化推薦系統(tǒng)基于社交關(guān)系體現(xiàn)用戶間相似性這一假設(shè),對解決傳統(tǒng)推薦系統(tǒng)中存在的冷啟動問題及提高推薦結(jié)果的準(zhǔn)確性具有重要作用。但社會化推薦系統(tǒng)天然開放性的特點,使其容易受到托攻擊者注入虛假欺騙信息(虛假評分或虛假關(guān)系等)的影響。此類攻擊稱為“托攻擊”,托攻擊嚴(yán)重影響了推薦結(jié)果的公正性和真實性,降低了用戶對系統(tǒng)的信任度。社會化推薦系統(tǒng)可以看成是傳統(tǒng)推薦系統(tǒng)與在線社交網(wǎng)絡(luò)結(jié)合的產(chǎn)物�，F(xiàn)有研究大多關(guān)注評分驅(qū)動的推薦系統(tǒng)或關(guān)系驅(qū)動的社交網(wǎng)絡(luò)中托攻擊的檢測問題,而較少關(guān)注同時受評分和關(guān)系驅(qū)動的社會化推薦系統(tǒng)可能受到的攻擊形式與檢測手段。針對現(xiàn)有研究的不足,本文首先對社會化推薦系統(tǒng)中的托攻擊者的行為方式進(jìn)行建模,然后提出用于檢測推薦系統(tǒng)與社交網(wǎng)絡(luò)中虛假欺騙信息的特征提取方法,進(jìn)而得到社會化推薦系統(tǒng)中的托攻擊檢測技術(shù)。本文分別從以下幾個方面展開研究:(1)構(gòu)建面向社會化推薦系統(tǒng)的托攻擊模型,并從攻擊成本與攻擊效果角度對所提模型進(jìn)行分析。托攻擊模型是托攻擊者向系統(tǒng)注入虛假用戶概貌的手段。通過分析現(xiàn)有社會化推薦技術(shù)的工作原理,歸納出托攻擊者可能的攻擊形式,從而提出托攻擊模型。然后分析攻擊模型對推薦結(jié)果的影響得到所提托攻擊模型對社會化推薦系統(tǒng)的攻擊效果。(2)針對評分驅(qū)動的推薦系統(tǒng)中的托攻擊問題,提出一種基于流行度分類特征的托攻擊檢測方法。推薦系統(tǒng)中托攻擊者通過注入虛假評分影響推薦結(jié)果,傳統(tǒng)方法大多從托攻擊者的評分方式入手,此類方法難以對新形式攻擊進(jìn)行檢測。為了解決這個問題,從托攻擊者與正常用戶不同的項目選擇行為入手,分析用戶概貌中項目流行度分布存在的差異,得到用于檢測推薦系統(tǒng)托攻擊的特征提取方法,最后結(jié)合分類器對推薦系統(tǒng)中的托攻擊進(jìn)行檢測。(3)針對關(guān)系驅(qū)動的社交網(wǎng)絡(luò)中的托攻擊問題,提出一種基于拉普拉斯得分的托攻擊檢測方法。社交網(wǎng)絡(luò)中托攻擊者通過注入虛假關(guān)系提升自己的影響力,從而達(dá)到傳播虛假信息的目的�，F(xiàn)有方法在訓(xùn)練模型時使用的特征維度較高,造成檢測準(zhǔn)確性不足。為了解決這個問題,提出無監(jiān)督的特征選擇方法,該方法通過拉普拉斯得分衡量特征的局部信息保持能力,以進(jìn)行特征選擇。在此基礎(chǔ)上,結(jié)合半監(jiān)督學(xué)習(xí)方法對社交網(wǎng)絡(luò)中的托攻擊進(jìn)行檢測。(4)面向社會化推薦系統(tǒng)中的托攻擊檢測問題,提出一種基于半監(jiān)督協(xié)同訓(xùn)練的社會化推薦系統(tǒng)托攻擊檢測方法。社會化推薦系統(tǒng)中的用戶包括評分特征與關(guān)系特征,因此可以利用推薦系統(tǒng)與社交網(wǎng)絡(luò)中檢測托攻擊的特征提取方法,得到用戶評分視圖與關(guān)系視圖的特征。同時考慮到系統(tǒng)中標(biāo)簽不足問題,將半監(jiān)督協(xié)同訓(xùn)練算法用于模型構(gòu)建,在兩個獨立的特征子圖上分別訓(xùn)練分類器,從而對社會化推薦系統(tǒng)中的托攻擊進(jìn)行檢測。
[Abstract]:With the rapid development of e-commerce and the rise of social network marketing, the social relationship between users as an additional input becomes the new research direction. The social recommendation system is based on the assumption that the social relation reflects the inter-user similarity, and plays an important role in solving the cold start problem existing in the traditional recommendation system and improving the accuracy of the recommendation result. But the nature of the self-opening of the social recommendation system makes it vulnerable to the influence of the false-lying information (false score or false relationship) injected by the attacker. This kind of attack is called "to attack", and the support attack seriously affects the fairness and the authenticity of the recommendation result, and reduces the user's trust in the system. The social recommendation system can be regarded as a product of the traditional recommendation system and the online social network. The existing research focuses on the detection of the support attack in the recommendation system or relationship driven by the score drive, while the less attention is paid to the form of attack and the means of detection of the social recommendation system driven by the scoring and the relationship. In view of the shortcomings of the existing research, this paper firstly models the behavior of the attacker in the social recommendation system, and then puts forward a feature extraction method for detecting the false spoofed information in the recommendation system and the social network, And then the carrier attack detection technology in the social recommendation system is obtained. This paper studies from the following aspects: (1) to construct a support attack model for the social recommendation system, and to analyze the proposed model from the attack cost and the attack effect angle. The support attack model is a means to allow an attacker to inject a false user profile into the system. Based on the analysis of the working principle of the existing social recommendation technology, the possible attack form of the attacker is summarized, and the attack model is put forward. Then the influence of the analysis attack model on the recommendation result is obtained, and the attack effect of the proposed attack model on the socialization recommendation system is obtained. (2) In order to solve the problem of support attack in the recommendation system driven by the score, a method for detecting the support attack based on the feature of the popularity classification is proposed. In the proposed system, it is difficult to detect the new forms of attack by injecting false scores to influence the recommended results. in ord to solve that problem, starting with different project selection behaviors of an attacker and a normal user, the difference in the distribution of the project popularity in the profile of a user is analyzed to obtain a feature extraction method for detecting a recommended system to attack, And finally, combining the classifier to detect the support attack in the recommendation system. (3) To solve the problem of the support attack in the social network driven by the relation, a method for detecting the support attack based on the Laplacian score is proposed. An attacker in a social network raises his influence by injecting a false relationship, thereby achieving the purpose of propagating false information. The method has the advantages that the characteristic dimension used in the training model is high, and the detection accuracy is insufficient. In order to solve this problem, a non-supervised feature selection method is proposed, which measures the local information retention capability of the feature by the Laplacian score for feature selection. On this basis, a semi-supervised learning method is used to detect the support attack in the social network. (4) In order to solve the problem of support attack detection in the social recommendation system, a method for detecting the support attack of the socialization recommendation system based on the semi-supervised cooperative training is proposed. The user of the social recommendation system includes the score feature and the relationship feature, so that the feature of the user's scoring view and the relationship view can be obtained by using the recommendation system and the feature extraction method of detecting the tray attack in the social network. At the same time, the semi-supervised cooperative training algorithm is used for the model construction, and the classifier is trained on two independent feature subgraphs, so that the support attack in the social recommendation system is detected.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.3
本文編號：2447403
[Abstract]:With the rapid development of e-commerce and the rise of social network marketing, the social relationship between users as an additional input becomes the new research direction. The social recommendation system is based on the assumption that the social relation reflects the inter-user similarity, and plays an important role in solving the cold start problem existing in the traditional recommendation system and improving the accuracy of the recommendation result. But the nature of the self-opening of the social recommendation system makes it vulnerable to the influence of the false-lying information (false score or false relationship) injected by the attacker. This kind of attack is called "to attack", and the support attack seriously affects the fairness and the authenticity of the recommendation result, and reduces the user's trust in the system. The social recommendation system can be regarded as a product of the traditional recommendation system and the online social network. The existing research focuses on the detection of the support attack in the recommendation system or relationship driven by the score drive, while the less attention is paid to the form of attack and the means of detection of the social recommendation system driven by the scoring and the relationship. In view of the shortcomings of the existing research, this paper firstly models the behavior of the attacker in the social recommendation system, and then puts forward a feature extraction method for detecting the false spoofed information in the recommendation system and the social network, And then the carrier attack detection technology in the social recommendation system is obtained. This paper studies from the following aspects: (1) to construct a support attack model for the social recommendation system, and to analyze the proposed model from the attack cost and the attack effect angle. The support attack model is a means to allow an attacker to inject a false user profile into the system. Based on the analysis of the working principle of the existing social recommendation technology, the possible attack form of the attacker is summarized, and the attack model is put forward. Then the influence of the analysis attack model on the recommendation result is obtained, and the attack effect of the proposed attack model on the socialization recommendation system is obtained. (2) In order to solve the problem of support attack in the recommendation system driven by the score, a method for detecting the support attack based on the feature of the popularity classification is proposed. In the proposed system, it is difficult to detect the new forms of attack by injecting false scores to influence the recommended results. in ord to solve that problem, starting with different project selection behaviors of an attacker and a normal user, the difference in the distribution of the project popularity in the profile of a user is analyzed to obtain a feature extraction method for detecting a recommended system to attack, And finally, combining the classifier to detect the support attack in the recommendation system. (3) To solve the problem of the support attack in the social network driven by the relation, a method for detecting the support attack based on the Laplacian score is proposed. An attacker in a social network raises his influence by injecting a false relationship, thereby achieving the purpose of propagating false information. The method has the advantages that the characteristic dimension used in the training model is high, and the detection accuracy is insufficient. In order to solve this problem, a non-supervised feature selection method is proposed, which measures the local information retention capability of the feature by the Laplacian score for feature selection. On this basis, a semi-supervised learning method is used to detect the support attack in the social network. (4) In order to solve the problem of support attack detection in the social recommendation system, a method for detecting the support attack of the socialization recommendation system based on the semi-supervised cooperative training is proposed. The user of the social recommendation system includes the score feature and the relationship feature, so that the feature of the user's scoring view and the relationship view can be obtained by using the recommendation system and the feature extraction method of detecting the tray attack in the social network. At the same time, the semi-supervised cooperative training algorithm is used for the model construction, and the classifier is trained on two independent feature subgraphs, so that the support attack in the social recommendation system is detected.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.3
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 楊k;鈕心忻;黃瑋;;基于協(xié)同譜聚類的推薦系統(tǒng)托攻擊防御算法[J];北京郵電大學(xué)學(xué)報;2015年06期
2 孟祥武;劉樹棟;張玉潔;胡勛;;社會化推薦系統(tǒng)研究[J];軟件學(xué)報;2015年06期
3 趙洪涌;朱霖河;;社交網(wǎng)絡(luò)中謠言傳播動力學(xué)研究[J];南京航空航天大學(xué)學(xué)報;2015年03期
4 程曉濤;劉彩霞;劉樹新;;基于關(guān)系圖特征的微博水軍發(fā)現(xiàn)方法[J];自動化學(xué)報;2015年09期
5 張玉清;呂少卿;范丹;;在線社交網(wǎng)絡(luò)中異常帳號檢測方法研究[J];計算機學(xué)報;2015年10期
6 鄒本友;李翠平;譚力文;陳紅;王紹卿;;基于用戶信任和張量分解的社會網(wǎng)絡(luò)推薦[J];軟件學(xué)報;2014年12期
7 劉建偉;劉媛;羅雄麟;;半監(jiān)督學(xué)習(xí)方法[J];計算機學(xué)報;2015年08期
8 周超;李博;;一種基于用戶信任網(wǎng)絡(luò)的推薦方法[J];北京郵電大學(xué)學(xué)報;2014年04期
9 胡祥;王文東;龔向陽;王柏;闕喜戎;;基于流形排序的社會化推薦方法[J];北京郵電大學(xué)學(xué)報;2014年03期
10 伍之昂;王有權(quán);曹杰;;推薦系統(tǒng)托攻擊模型與檢測技術(shù)[J];科學(xué)通報;2014年07期
，本文編號：2447403
本文鏈接：http://sikaile.net/jingjilunwen/dianzishangwulunwen/2447403.html
最近更新
教材專著
