A Contrast Metric for Fraud Detection in Rich Graphs

doi:10.1109/TKDE.2018.2876531

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	A Contrast Metric for Fraud Detection in Rich Graphs
	Liu, Shenghua 1; Hooi, Bryan 2; Faloutsos, Christos 2
刊名	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
	2019-12-01
卷号	31 期号:12 页码:2235-2248
关键词	Image edge detection Topology Measurement Robustness Time series analysis Tensile stress Manuals Graph mining time series fraud detection contrast suspiciousness
ISSN号	1041-4347
DOI	10.1109/TKDE.2018.2876531
英文摘要	How can we detect fraud in a big graph with rich properties, as online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, to hide their fraudulent attacks? To achieve robustness, existing approaches detected dense sub-graphs as suspicious patterns in an unsupervised way, such as average degree maximization. However, such approaches suffer from the bias of including more nodes than necessary, resulting in lower accuracy and increased need for manual verification. Therefore, we propose HoloScope, which introduces a novel metric "contrast suspiciousness" integrating information from graph topology and spikes to more accurately detect fraudulent users and objects. Contrast suspiciousness dynamically emphasizes the contrasting patterns between fraudsters and normal users, making HoloScope capable of distinguishing the synchronized and strange behaviors of fraudsters by means of topology, bursts and drops, and rating scores. In addition, we provide theoretical bounds for how much this method increases the time cost needed for fraudsters to conduct adversarial attacks. Moreover, HoloScope has a concise framework and sub-quadratic time complexity, making the algorithm reproducible and scalable. In extensive experiments, HoloScope achieved significant accuracy improvements on real data with injected labels and true labels, when compared with state-of-the-art fraud detection methods.
资助项目	Strategic Priority Research Program of CAS[XDA19020400] ; National 973 Program of China[2014CB340401] ; NSF of China[61772498] ; NSF of China[61872206] ; Beijing NSF[4172059] ; Army Research Laboratory[W911NF-09-2-0053] ; China Scholarship Council
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000498653800001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/14922]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Shenghua
作者单位	1.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100864, Peoples R China 2.Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
推荐引用方式 GB/T 7714	Liu, Shenghua,Hooi, Bryan,Faloutsos, Christos. A Contrast Metric for Fraud Detection in Rich Graphs[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2019,31(12):2235-2248.
APA	Liu, Shenghua,Hooi, Bryan,&Faloutsos, Christos.(2019).A Contrast Metric for Fraud Detection in Rich Graphs.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,31(12),2235-2248.
MLA	Liu, Shenghua,et al."A Contrast Metric for Fraud Detection in Rich Graphs".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 31.12(2019):2235-2248.