1,126 Hits in 3.4 sec

Scalable anomaly detection in blockchain using graphics processing unit

Shin Morishima
2021 Computers & electrical engineering  
In this paper, we propose a subgraph-based anomaly detection method to perform the detection using a part of the blockchain data.  ...  The proposed structure of the subgraph is suitable for graphics processing units (GPUs) to accelerate detection by using parallel processing.  ...  In this structure, the creation of the subgraph, feature extraction, and anomaly detection are performed on the GPU.  ... 
doi:10.1016/j.compeleceng.2021.107087 fatcat:hkm7owmjkna4vc2cqcywdhtwfq

Quick survey of graph-based fraud detection methods [article]

Paul Irofti, Andrei Patrascu, Andra Baltoiu
2021 arXiv   pre-print
In general, anomaly detection is the problem of distinguishing between normal data samples with well defined patterns or signatures and those that do not conform to the expected profiles.  ...  Most commonly, these networks are represented as attributed graphs, with numerical features complementing relational information.  ...  A modularized anomaly detection hierarchical framework has been developed in [2] to detect static anomalous connected subgraphs, with high average weights.  ... 
arXiv:1910.11299v3 fatcat:zyupd4ezxrgw3f7g5utzihy6qi

Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks [article]

Jiaqiang Zhang, Senzhang Wang, Songcan Chen
2022 arXiv   pre-print
This paper proposes a self-supervised learning framework that jointly optimizes a multi-view contrastive learning-based module and an attribute reconstruction-based module to more accurately detect anomalies  ...  This task is challenging due to both the complex interactions between the anomalous nodes with other counterparts and their inconsistency in terms of attributes.  ...  Subgraph Sampling. We adopt random walk with restart (RWR) [Tong et al., 2006] to sample the local subgraph. In both views, a subgraph with the size P is sampled for each node.  ... 
arXiv:2205.04816v1 fatcat:r6v76enibnaqzne3hrgbv6i3oi

Anomaly Mining – Past, Present and Future [article]

Leman Akoglu
2021 arXiv   pre-print
I conclude with key take-aways and overarching open problems.  ...  In this article, I focus on two areas, (1) point-cloud and (2) graph-based anomaly mining.  ...  Defining Graph Anomalies Graph anomalies can be organized into three main classes of problems: (i) node/edge-level, (ii) subgraph-level, and (iii) graph-level anomaly detection.  ... 
arXiv:2105.10077v2 fatcat:znvvz6ewpbdpjhnhp35kudvzlu

AntiBenford Subgraphs: Unsupervised Anomaly Detection in Financial Networks [article]

Tianyi Chen, Charalampos E. Tsourakakis
2022 arXiv   pre-print
We show empirically that our proposed framework enables the detection of anomalous subgraphs in cryptocurrency transaction networks that go undetected by state-of-the-art graph-based anomaly detection  ...  We propose the AntiBenford subgraph framework that is founded on well-established statistical principles.  ...  Noble and Cook [55] studied anomaly detection on graphs with categorical features by searching for graph sub-structures that occur infrequently.  ... 
arXiv:2205.13426v1 fatcat:3sbd7ke7tzedza2hxdcdn7wagq

FadMan: Federated Anomaly Detection across Multiple Attributed Networks [article]

Nannan Wu, Ning Zhang, Wenjun Wang, Lixin Fan, Qiang Yang
2022 arXiv   pre-print
In each private attributed network, the detected anomaly subgraph is aligned with an anomaly subgraph in the public attributed network.  ...  The proposed algorithm FadMan is a vertical federated learning framework for public node aligned with many private nodes of different features, and is validated on two tasks correlated anomaly detection  ...  It is a method of detecting anomaly subgraphs of the graph based on anomaly features of another graph.  ... 
arXiv:2205.14196v1 fatcat:rsiyizttvfgbnehb4k5fxj3keu


Leman Akoglu, Duen Horng Chau, U. Kang, Danai Koutra, Christos Faloutsos
2012 Proceedings of the 2012 international conference on Management of Data - SIGMOD '12  
Detection module (OddBall) uses graph statistics to mine patterns and spot anomalies, such as nodes with many contacts but few interactions with them (possibly telemarketers); (3) The Interactive Visualization  ...  Given a large graph with millions or billions of nodes and edges, like a who-follows-whom Twitter graph, how do we scalably compute its statistics, summarize its patterns, spot anomalies, visualize and  ...  Anomaly Detection The anomaly detection module OddBall [1] consists of three main components: (1) feature extraction, (2) pattern mining, and (3) anomaly detection.  ... 
doi:10.1145/2213836.2213941 dblp:conf/sigmod/AkogluCKKF12 fatcat:oj7arrwbvzf33ivfphz2llib4e

Anomaly Detection in Graphs of Bank Transactions for Anti Money Laundering Applications

Bogdan Dumitrescu, Andra Baltoiu, Stefania Budulan
2022 IEEE Access  
Our features are added to usual egonet features and a general anomaly detection algorithm, in our case Isolation Forest, serves to detect the anomalies.  ...  Our method is based on designing new features; the most important are those resulting from the reduced egonet, which is the subgraph that remains from an egonet after eliminating the nodes connected with  ...  ANOMALY DETECTION ALGORITHMS We combine now the features defined in Section IV in sets of features to be used for anomaly detection.  ... 
doi:10.1109/access.2022.3170467 fatcat:vbblqcmyczgmfop2blz6gt5i7a

Anomaly detection in dynamic networks: a survey

Stephen Ranshous, Shitian Shen, Danai Koutra, Steve Harenberg, Christos Faloutsos, Nagiza F. Samatova
2015 Wiley Interdisciplinary Reviews: Computational Statistics  
Anomaly detection is an important problem with multiple applications, and thus has been studied for decades in various research domains.  ...  An important problem over dynamic networks is anomaly detection-finding objects, relationships, or  ...  In addition, this material is based upon work supported in part with funding from the Laboratory for Analytic Sciences.  ... 
doi:10.1002/wics.1347 fatcat:44znvnsmlfcgfbbljcvmuubgpi

Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [article]

Yixin Liu, Zhao Li, Shirui Pan, Chen Gong, Chuan Zhou, George Karypis
2021 arXiv   pre-print
Recently, the deep learning-based anomaly detection methods have shown promising results over shallow approaches, especially on networks with high-dimensional attributes and complex structures.  ...  In this way, the learning model is trained by a specific anomaly detection-aware target.  ...  Secondly, their reconstructive optimization target is not associated with anomaly detection.  ... 
arXiv:2103.00113v1 fatcat:gep7h2b4qrhzxbpnqsjbu7xmsi

Graph-based Anomaly Detection and Description: A Survey [article]

Leman Akoglu and Hanghang Tong and Danai Koutra
2014 arXiv   pre-print
Detecting anomalies in data is a vital task, with numerous high-impact applications in areas such as security, finance, health care, and law enforcement.  ...  As objects in graphs have long-range correlations, a suite of novel technology has been developed for anomaly detection in graph data.  ...  2003] [0, 1] subgraph anomaly score subgraphs SUBDUE [Eberle and Holder, 2007] [0, ∞] subgraph anomaly score modified subgraphs binary graph classification graphs with traced-back crashing points  ... 
arXiv:1404.4679v2 fatcat:y6nsswymcfc2pa7qe7zrjzc7wq

Graph based anomaly detection and description: a survey

Leman Akoglu, Hanghang Tong, Danai Koutra
2014 Data mining and knowledge discovery  
Detecting anomalies in data is a vital task, with numerous high-impact applications in areas such as security, finance, health care, and law enforcement.  ...  As objects in graphs have long-range correlations, a suite of novel technology has been developed for anomaly detection in graph data.  ...  [Noble and Cook, 2003] [0, 1] subgraph anomaly score subgraphs SUBDUE [Eberle and Holder, 2007] [0, ∞] subgraph anomaly score modified subgraphs [Liu et al., 2005] binary graph classification graphs  ... 
doi:10.1007/s10618-014-0365-y fatcat:rfjn7bwdgra5faorwbdkkb45ze

Debugging OpenStack Problems Using a State Graph Approach [article]

Yong Xiang, Hu Li, Sen Wang, Wei Xu
2016 arXiv   pre-print
Also, using graph-based anomaly detection, we can automatically discover hidden problems in OpenStack.  ...  It is hard to operate and debug systems like OpenStack that integrate many independently developed modules with multiple levels of abstractions.  ...  The anomaly detection algorithm captures a subgraph, with relevant portion shown in Figure 3(b) .  ... 
arXiv:1606.05963v1 fatcat:tgpbimmycncmrnr5vmyqqsthu4

Uncovering Specific-Shape Graph Anomalies in Attributed Graphs

Nannan Wu, Wenjun Wang, Feng Chen, Jianxin Li, Bo Li, Jinpeng Huai
However, the specific-shape priors about anomalous subgraphs of interest are seldom considered by the traditional approaches when detecting the subgraphs in attributed graphs (e.g., computer networks,  ...  This paper proposes a nonlinear approach to specific-shape graph anomaly detection.  ...  connected subgraph anomaly detection.  ... 
doi:10.1609/aaai.v33i01.33015433 fatcat:zvksefw4ejgjbkmx4ms6ql3eku

Using Consensus Clustering for Multi-view Anomaly Detection

Alexander Y. Liu, Dung N. Lam
2012 2012 IEEE Symposium on Security and Privacy Workshops  
To avoid detection, these malicious insiders want to appear as normal as possible with respect to the activities of other users with similar privileges and tasks.  ...  An anomaly may only be apparent when analyzing multiple sources of data. We propose and test domain-independent methods that combine consensus clustering and anomaly detection techniques.  ...  Other forms of anomaly detection for categorical features are possible and are being tested as part of ongoing work.  ... 
doi:10.1109/spw.2012.18 dblp:conf/sp/LiuL12 fatcat:v2mlakkbufcf5dqyeghx77k7vm
« Previous Showing results 1 — 15 out of 1,126 results