arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.08149cs.AIcs.LGstat.ML
收藏

面向异构数据异常检测的多输入变分自编码器

Multiple-Input Variational Auto-Encoder for Anomaly Detection in Heterogeneous Data

School of Electrical and Data Engineering, the University of Technology Sydney(悉尼科技大学电气与数据工程学院);Le Quy Don Technical University(黎贵敦技术大学)

Phai Vu Dinh, Diep N. Nguyen, Dinh Thai Hoang, Quang Uy Nguyen, Eryk Dutkiewicz

AI总结:

针对异构数据异常检测的特征子集异构性难题,提出MIAEAD和MIVAE两种模型,通过子编码器处理特征子集,经理论证明和8个真实数据集实验验证,性能优于现有方法,AUC最高提升6%。

摘要:

异常检测(AD)在人工智能应用中发挥着关键作用,例如分类任务以及网络安全领域的入侵/威胁检测。然而,现有大多数方法都面临由非独立同分布(non-IID)数据带来的特征子集间异构性挑战。我们提出了一种名为多输入自编码器异常检测模型(Multiple-Input Auto-Encoder for AD, MIAEAD)的新型神经网络模型以解决该问题。MIAEAD会为数据样本的每个特征子集分配一个异常分数,用于指示其为异常的可能性,具体方式是将对应子编码器的重构误差作为异常分数。所有子编码器随后通过无监督学习同步训练,以确定各特征子集的异常分数。MIAEAD的最终AUC(受试者工作特征曲线下面积)会针对每个子数据集计算,并选取所有子数据集中获得的最大AUC值。为了利用生成式模型对正常数据分布的建模能力来识别异常,我们开发了一种名为多输入变分自编码器(Multiple-Input Variational Auto-Encoder, MIVAE)的新型神经网络架构/模型。MIVAE可通过其子编码器处理各特征子集,再在潜在空间中学习正常数据的分布,这使得MIVAE能够识别出偏离所学分布的异常。我们从理论上证明,所提出的MIVAE得到的正常样本与异常样本的平均异常分数差值,大于变分自编码器异常检测模型(Variational Auto-Encoder, VAEAD)的对应差值,因此MIVAE能取得更高的AUC。在8个真实世界异常数据集上开展的大量实验表明,MIAEAD和MIVAE的性能优于传统方法以及当前最优的无监督模型,AUC分数最高提升6%。此外,当应用于基于变异系数(CV)得分判定的低异构性特征子集时,MIAEAD和MIVAE也能取得较高的AUC。

英文摘要:

Anomaly detection (AD) plays a pivotal role in AI applications, e.g., in classification, and intrusion/threat detection in cybersecurity. However, most existing methods face challenges of heterogeneity amongst feature subsets posed by non-independent and identically distributed (non-IID) data. We propose a novel neural network model called Multiple-Input Auto-Encoder for AD (MIAEAD) to address this. MIAEAD assigns an anomaly score to each feature subset of a data sample to indicate its likelihood of being an anomaly. This is done by using the reconstruction error of its sub-encoder as the anomaly score. All sub-encoders are then simultaneously trained using unsupervised learning to determine the anomaly scores of feature subsets. The final AUC of MIAEAD is calculated for each sub-dataset, and the maximum AUC obtained among the sub-datasets is selected. To leverage the modelling of the distribution of normal data to identify anomalies of the generative models, we develop a novel neural network architecture/model called Multiple-Input Variational Auto-Encoder (MIVAE). MIVAE can process feature subsets through its sub-encoders before learning distribution of normal data in the latent space. This allows MIVAE to identify anomalies that deviate from the learned distribution. We theoretically prove that the difference in the average anomaly score between normal samples and anomalies obtained by the proposed MIVAE is greater than that of the Variational Auto-Encoder (VAEAD), resulting in a higher AUC for MIVAE. Extensive experiments on eight real-world anomaly datasets demonstrate the superior performance of MIAEAD and MIVAE over conventional methods and the state-of-the-art unsupervised models, by up to 6% in terms of AUC score. Alternatively, MIAEAD and MIVAE have a high AUC when applied to feature subsets with low heterogeneity based on the coefficient of variation (CV) score.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑