Pattern Discovery and Anomaly Detection via Knowledge Graph

Jia, Bin; Dong, Cailing; Chen, Z.; Chang, Kuo‐Chu; Sullivan, Nichole; Chen, Genshe

doi:10.23919/icif.2018.8455737

Cited by 13 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple studies have considered detection of anomalies using graph data [23]. More recently, several of these methods have focused on multi-relational data, as found in knowledge graphs [24,25,26]. In fact, knowledge graph completion methods, able by definition to infer missing facts, can be readily applied to anomaly detection problems [27].…”

Section: Learning Methodsmentioning

confidence: 99%

Machine learning on knowledge graphs for context-aware security monitoring

Garrido

Dold

Frank

2021

2021 IEEE International Conference on Cyber Security and Resilience (CSR)

View full text Add to dashboard Cite

Machine learning techniques are gaining attention in the context of intrusion detection due to the increasing amounts of data generated by monitoring tools, as well as the sophistication displayed by attackers in hiding their activity. However, existing methods often exhibit important limitations in terms of the quantity and relevance of the generated alerts. Recently, knowledge graphs are finding application in the cybersecurity domain, showing the potential to alleviate some of these drawbacks thanks to their ability to seamlessly integrate data from multiple domains using human-understandable vocabularies. We discuss the application of machine learning on knowledge graphs for intrusion detection and experimentally evaluate a link-prediction method for scoring anomalous activity in industrial systems. After initial unsupervised training, the proposed method is shown to produce intuitively well-calibrated and interpretable alerts in a diverse range of scenarios, hinting at the potential benefits of relational machine learning on knowledge graphs for intrusion detection purposes.

show abstract

Section: Learning Methodsmentioning

confidence: 99%

Machine learning on knowledge graphs for context-aware security monitoring

Garrido

Dold

Frank

2021

2021 IEEE International Conference on Cyber Security and Resilience (CSR)

View full text Add to dashboard Cite

show abstract

“…The time of day can be divided into four time intervals. We set four intervals of the hour: [0, 3), [6,11), [15,24), and [3, 6) ∪ [11,15), according to the time distribution in transactions. We further divide the attribute time into 8 unique values by distinguishing whether it is a weekday.…”

Section: Datasetsmentioning

confidence: 99%

“…As the main contribution of our work, we aim to effectively model the co-occurrences among transactional attributes for high-performance behavioral models. For this purpose, we propose to adopt the heterogeneous relation network, a special form of the knowledge graph [15], to represent the co-occurrences effectively. Here, a network node (or say an entity) corresponds to an attribute value in transactions, and an edge corresponds to a heterogeneous association between different attribute values.…”

Section: Introductionmentioning

confidence: 99%

Representing Fine-Grained Co-Occurrences for Behavior-Based Fraud Detection in Online Payment Services

Wang

Zhu

2022

IEEE Trans. Dependable and Secure Comput.

View full text Add to dashboard Cite

The vigorous development of e-commerce breeds cybercrime. Online payment fraud detection, a challenge faced by online service, plays an important role in rapidly evolving e-commerce. Behavior-based methods are recognized as a promising method for online payment fraud detection. However, it is a big challenge to build high-resolution behavioral models by using low-quality behavioral data. In this work, we mainly address this problem from data enhancement for behavioral modeling. We extract fine-grained co-occurrence relationships of transactional attributes by using a knowledge graph. Furthermore, we adopt the heterogeneous network embedding to learn and improve representing comprehensive relationships. Particularly, we explore customized network embedding schemes for different types of behavioral models, such as the population-level models, individual-level models, and generalized-agentbased models. The performance gain of our method is validated by the experiments over the real dataset from a commercial bank. It can help representative behavioral models improve significantly the performance of online banking payment fraud detection. To the best of our knowledge, this is the first work to realize data enhancement for diversified behavior models by implementing network embedding algorithms on attribute-level co-occurrence relationships.

show abstract

“…In complex networked systems (CNS), structural observability determines the number of nodes to be measured to [10], [22], [23], [24], [25], [26], [27], [28] Link prediction [29], [30], [31], [32], [33], [34], [35], [36], [37] Node classification [38], [39], [40], [41] Synchronization [42], [43], [44], [45], [46], [47], [48], [49], [50] Controllability [10], [22], [51], [25], [26], [27], [28] Anomaly detection [52], [53], [54], [55], [56], [57], [58], [59], [60] Topological analysis [5], [61], [62],…”

Section: A Prerequisites Of Setting and Fulfilling Model's Aimsmentioning

confidence: 99%

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Wen¹,

Gabrys²,

Musiał³

2022

Preprint

View full text Add to dashboard Cite

This paper aims to provide a comprehensive critical overview on how entities and their interactions in Complex Networked Systems (CNS) are modelled across disciplines as they approach their ultimate goal of creating a Digital Twin (DT) that perfectly matches the reality. We propose a new framework to conceptually compare diverse existing modelling paradigms from different perspectives and create unified assessment criteria to assess their respective capabilities of reaching such an ultimate goal. Using the proposed criteria, we also appraise how far the reviewed current state-of-the-art approaches are from the idealised DTs. We also identify and propose potential directions and ways of building a DT-orientated CNS based on the convergence and integration of CNS and DT utilising a variety of cross-disciplinary techniques.

show abstract

Pattern Discovery and Anomaly Detection via Knowledge Graph

Cited by 13 publications

References 5 publications

Machine learning on knowledge graphs for context-aware security monitoring

Machine learning on knowledge graphs for context-aware security monitoring

Representing Fine-Grained Co-Occurrences for Behavior-Based Fraud Detection in Online Payment Services

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Contact Info

Product

Resources

About