2020
DOI: 10.1007/978-3-030-65745-1_8
|View full text |Cite
|
Sign up to set email alerts
|

Graph Deep Learning Based Anomaly Detection in Ethereum Blockchain Network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
18
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 32 publications
(18 citation statements)
references
References 14 publications
0
18
0
Order By: Relevance
“…At this moment, some blockchain anomaly detection methods have been proposed. Vatsal et al [28] used a One-Class Graph Neural Network-based anomaly detection framework for detecting anomalies in the Ethereum blockchain network. Sayadi et al [29] used One-Class Support Vector Machine (OCSVM) used planar separation of normal and abnormal data in a high-dimensional feature space, which is eventually used to identify anomalies in the Bitcoin network.…”
Section: Related Workmentioning
confidence: 99%
“…At this moment, some blockchain anomaly detection methods have been proposed. Vatsal et al [28] used a One-Class Graph Neural Network-based anomaly detection framework for detecting anomalies in the Ethereum blockchain network. Sayadi et al [29] used One-Class Support Vector Machine (OCSVM) used planar separation of normal and abnormal data in a high-dimensional feature space, which is eventually used to identify anomalies in the Bitcoin network.…”
Section: Related Workmentioning
confidence: 99%
“…Visualising blockchain transactions as graphs by using the algorithms proposed in section II is much appropriate to extract meaningful patterns than the traditional database representation. This will produce an informative dataset for different graph-based analysis [7] like anomaly detection, predict ransomware transaction, identification of illicit marketrelated trades, cryptocurrency's market trend for future investments, etc.…”
Section: Graph Based Visualization Of Anomaly Blockchain Transactionsmentioning
confidence: 99%
“…Moreover, it will meet various challenges when performing data analysis in terms of processing power, time and memory. Due to these reasons, there is an increased interest in the graph-based visualisation and graph-based analysis [7] of blockchain transactions. The graph-based representation enriches the data by incorporating the relations between transactions and facilitate navigation through the transactions without the need for complex queries to join combinations of tables together as in the relational model.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Patel et al [78] presented a one-class graph deep learning framework for anomaly detection on the Ethereum blockchain. To create a data set, they collected the external transactions from the Ethereum blockchain, marked the anomalies manually, and extracted the needed features.…”
Section: Data Processingmentioning
confidence: 99%