상세정보
Export to Refworks부가기능
Attackers' Intention and Influence Analysis in Social Media
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Attackers' Intention and Influence Analysis in Social Media. |
| 개인저자 | Lai, Chun-Ming. |
| 단체저자명 | University of California, Davis. Computer Science. |
| 발행사항 | [S.l.]: University of California, Davis., 2019. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
| 형태사항 | 95 p. |
| 기본자료 저록 | Dissertations Abstracts International 81-04A. Dissertation Abstract International |
| ISBN | 9781085795845 |
| 학위논문주기 | Thesis (Ph.D.)--University of California, Davis, 2019. |
| 일반주기 |
Source: Dissertations Abstracts International, Volume: 81-04, Section: A.
Advisor: Wu, S. Felix. |
| 이용제한사항 | This item must not be sold to any third party vendors. |
| 요약 | Human communication behavior has changed significantly with the popularity of Online Social Networks (OSNs). In the absence of access control mechanisms, any user can contribute to an OSNs thread. Individuals can exploit this characteristic to execute targeted attacks, which increases the potential for subsequent malicious behaviors such as phishing, hate speech, malware distribution and fake news propagation. Actually, new patterns of attacking strategies have been discovered, trying to influence OSNs users online and offline behavior implicitly and explicitly.In this dissertation, we will use the concepts from criminology to study attackers strategies on OSNs. Our examinations include: (1) The suitable targets problem studies the characteristic of those post threads embedded with malicious URLs. (2) Effectiveness and influence analysis quantify the reactions and feedbacks for malicious campaigns. (3) Attackers daily and weekly behavior vectors provide the other way to analyze how malicious accounts differ from normal ones. We apply all above problems into engineering framework consideration, aiming at designing a general predictive systems on large-scale OSNs datasets with state-of-the-art machine learning algorithms.To evaluate our model, we will use discussion threads from Facebook public pages. By our research, with limited resource, attackers are able to perform more intelligent and effective malicious campaigns. On the other hand, defenders can focus on suspected targets by certain temporal and spatial variables. It is our hope that the data and analyses presented in this proposal will support a better understanding of attacker strategies and footprints, thereby assisting digital forensics. |
| 일반주제명 | Computer science. Communication. Web studies. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
