Scalable anomaly detection in blockchain using graphics processing unit
Scalable anomaly detection in blockchain using graphics processing unit
复制标题
使用图形处理单元进行区块链中的可扩展异常检测
DOI：
10.1016/j.compeleceng.2021.107087
复制
发表时间：
2021
影响因子：
4.3
通讯作者：
Morishima Shin
中科院分区：
文献类型：
--
作者：
Yuya Sawa;Ryoichi Takashima;Tetsuya Takiguchi;Morishima Shin
在区块链中，与现有的银行交易不同，已批准的交易（包括非法交易）无法修改。为了防止非法交易造成的损害，需要对交易进行快速异常检测，因为交易可以在批准之前进行修改。然而，现有的异常检测方法必须处理区块链中的所有交易，并且处理时间长于每次批准的间隔。在本文中，我们提出了一种基于子图的异常检测方法，使用部分区块链数据进行检测。所提出的子图结构适用于图形处理单元（GPU），以加速检测通过使用并行处理。在使用真实的比特币交易数据的评估中，当目标交易数量为100时，所提出的方法比现有的基于GPU的方法快11.1倍，而不降低检测精度。
In blockchain, approved transactions, including illegal ones, cannot be modified unlike existing bank transactions. To prevent the damage caused by illegal transactions, rapid anomaly detection of transactions is required because transactions can be modified before approval. However, existing anomaly detection methods must process all transactions in blockchain, and the processing time is longer than the interval of each approval. 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 an evaluation using real Bitcoin transaction data, when the number of targeted transactions was one hundred, the proposed method was 11.1x faster than an existing GPU-based method without lowering the detection accuracy.