A Collective Anomaly Detection Approach for Multidimensional Streams in Mobile Service Security

Abstract

Anomaly detection in many applications is becoming more and more important, especially for security and privacy in mobile service computing domains with the development of mobile internet and mobile cloud computing, in which data are typical multidimensional time series data. However, the collective anomaly detection for multidimensional streams exists lots of problems, owing to the differences between the anomaly detection in multidimensional time series and univariate time series data. For example, the temporal continuity of multidimensional time series is much weaker than univariate time series and it is unreasonable to judge the entire multidimensional data as an anomaly if a certain dimension is abnormal. In this paper, we consider the statistical features of the subsequence of streams, proposing a novel collective anomaly detection algorithm for multidimensional streams based on iForest in a cloud environment, namely iForestFS. When using different features about mobile cloud services' metrics suggested by domain knowledge, iForestFS could detect different kinds of anomalies for mobile service security. Furthermore, we implement a distributed iForestFS using spark framework in order to improve time performance and scalability. The experimental results performed on three datasets (mainly about network security) derived from the UCI repository demonstrate that the proposed algorithm can effectively detect a collective anomaly of multidimensional streams in the security domain.INDEX TERMS Collective anomaly detection, time series, isolation forest, security in mobile service, multidimensional stream processing.

Anomalyzer: A Visual Interface for Multimodal Time Series Anomaly Analysis

“…Temporal transformations for extracting contextual information. In the context of anomaly detection within time series streams, the inherent contextual locality plays a critical role in identifying collective anomalies [4,5,27,28]. To harness these essential characteristics, our initial step involves the application of temporal…”

“…Similarly, smart buildings enhance energy efficiency by monitoring energy usage to identify abnormal consumption behavior and mitigate potential life-threatening disasters [4]. Additionally, anomaly detection has become essential for maintaining security and privacy in mobile service computing domains [5].…”

A Survey of Collective Anomaly Detection on Sequence Dataset

“…According to the distribution of normal sample sequences reflected by pB(x) and the distribution of the entire dataset reflected by pFB(x), it intends to detect collective anomalies with abnormal distribution pA(x). Maru and Kobayashi (2020) chose the regression model-based approach, Weng and Liu (2019) selected Gaussian model-based approaches, and H. Qin, X. Zhan, and Y. Zheng (2021) selected mixture distribution based approaches by analyzing data distribution, the degree of abnormality can be measured by either an abnormal feedback in mean, variance, or both.…”