東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Towards Online Heterogeneous Spam De...

Gao, Hongyu.

FindBook

Google Book

Amazon

博客來

Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks./
作者:	Gao, Hongyu.
面頁冊數:	118 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.
Contained By:	Dissertation Abstracts International75-01B(E).
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3595592
ISBN:	9781303414305

Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks.
Gao, Hongyu.

Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks. - 118 p.

Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.

Thesis (Ph.D.)--Northwestern University, 2013.

Online social networks (OSNs) are extremely popular among Internet users. However, spam originating from friends and acquaintances in OSNs not only reduces the joy of Internet surfing, but also may cause damage to less security-savvy users. While spam filtering techniques have been significantly advanced, spammers constantly adapt their spamming strategy to avoid detection.

ISBN: 9781303414305Subjects--Topical Terms:

626642
Computer Science.

Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks.
LDR:04087nam a2200313 4500 001 1959404
005 20140520124016.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303414305
035 $a (MiAaPQ)AAI3595592
035 $a AAI3595592
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gao, Hongyu. $3 2094817
245 1 0 $a Towards Online Heterogeneous Spam Detection and Mitigation for Online Social Networks.
300 $a 118 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.
500 $a Adviser: Yan Chen.
502 $a Thesis (Ph.D.)--Northwestern University, 2013.
520 $a Online social networks (OSNs) are extremely popular among Internet users. However, spam originating from friends and acquaintances in OSNs not only reduces the joy of Internet surfing, but also may cause damage to less security-savvy users. While spam filtering techniques have been significantly advanced, spammers constantly adapt their spamming strategy to avoid detection.
520 $a In this work, I develop Tangram, a framework that incorporates multiple heterogeneous techniques to mitigate OSN spam and to protect OSN users. The heterogeneous detection techniques attack spam from different angles and complement each other. The system is designed to integrate into the OSN platform. It inspects the user generated message stream and block spam message directly. The process is transparent to OSN users. Tangram contains three major detection modules: i) online campaign discovery module, ii) spam template generation module, and iii) malicious domain group detection module. The online campaign discovery module and the spam template generation module detect OSN spam online, whereas the malicious domain group detection module works offline. Although the offline module does not directly detects OSN spam, it supplies training samples to the online modules.
520 $a The online campaign discovery module exploits the intuition that spam messages are organized in campaigns. Further, the campaign structure can be identified by syntactical similarity between spam messages. Although syntactic-based campaign identification has been used for offline spam analysis, I apply this technique to aid the online spam detection problem with sufficiently low overhead. In addition, a set of novel features that effectively distinguish spam campaigns from legitimate similar message groups are developed. Evaluations show that this module achieves high true positive rate (80.9%) and decently low false positive rate (0.19%).
520 $a The spam template generation module targets a special type of spam generated with underlying templates, based on the measurement of captured OSN spam that shows the majority (63.0%) of it belongs to this type. The template generation technique automatically divides OSN spam messages into segments and uses the segments to construct templates to filter future spam. Experimental results show that it is extremely accurate to throttle template-based spam with 95.7% true positive rate. The induced false positive rate is also low (0.12%).
520 $a The malicious domain group detection module focuses on the temporal correlation between the domain query patterns to detect malicious domains. The detected domains are then used to identify OSN spam messages, thus generates training set for the online spam detection modules in the Tangram framework. Starting with known malicious domains as anchors, this module first identified other domains that exhibit strong temporal correlation with anchor domains in their query patterns. The identified domains are candidate malicious domains. After that, an additional refinement step clusters the candidate domains according to their query patterns to filter domains that are accidentally queried together with the anchor domains.
590 $a School code: 0163.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a Northwestern University. $b Computer Science. $3 1019334
773 0 $t Dissertation Abstracts International $g 75-01B(E).
790 $a 0163
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3595592