Universal Data Anomaly Detection via Inverse Generative Adversary Network
Universal Data Anomaly Detection via Inverse Generative Adversary Network
复制标题
DOI：
10.1109/lsp.2020.2978462
复制
发表时间：
2020-01
影响因子：
3.9
通讯作者：
Kursat Rasim Mestav;L. Tong
中科院分区：
文献类型：
--
作者：
Kursat Rasim Mestav;L. Tong
考虑了在未知概率分布下检测数据异常的问题。尽管无异常数据的概率分布尚不清楚，但假定无异常的训练样品可用。对于异常数据，既不知道的潜在概率分布也不可用。提出了一种深度学习方法，再加上基于巧合的统计检验，其中训练了一个反向生成对手网络，以将数据转换为经典统一与非均匀假设检验问题。所提出的方法对于检测持续异常特别有效，其分布与无异常分布的分布域具有重叠的域。
The problem of detecting data anomaly under unknown probability distributions is considered. Whereas the probability distribution of the anomaly-free data is unknown, anomaly-free training samples are assumed to be available. For anomaly data, neither the underlying probability distribution is known nor anomaly data samples are available. A deep learning approach coupled with a statistical test based on coincidence is proposed where an inverse generative adversary network is trained to transform data to the classical uniform vs. nonuniform hypothesis testing problem. The proposed approach is particularly effective to detect persistent anomalies whose distributions have an overlapping domain with that of the anomaly-free distribution.