A Systematic Review on Anomaly Detection for Cloud Computing Environments

Abstract

The detection of anomalies in data is a far-reaching field of research which also applies to the field of cloud computing in several different ways: from the detection of various types of intrusions to the detection of hardware failures, many publications address how far anomaly detection methods are able to meet the specific requirements of a cloud-based network. Since there is still no comprehensive overview of this constantly growing field of research, this literature review provides a systematic evaluation of 215 publications that can be considered as representative for the last ten years of this scientific development. Our analysis identifies three main methodological areas (machine learning, deep learning, statistical approaches) and summarizes how exactly the corresponding models are applied for the detection of anomalies. Furthermore, we clarify which concrete application areas are typically addressed by anomaly detection in the context of cloud computing environments and which related public datasets are often used for evaluations. Finally, we discuss the implications of the literature review and provide directions for future research.

A Survey of AI-Based Anomaly Detection in IoT and Sensor Networks

“…Application Focus [6] cloud computing IDS [5] computer networks IDS [24] malicious actor space and information networks [2] IIoT GNNs [23] attention-based AD - [4] attention-based AD - [1] non-IoT graph-based AD deep learning [3] general AD -…”

“…The work in [ 6 ] focuses on cloud computing in cloud computing environments. The paper highlights the length of time anomaly detection has been performed, with the earliest reference of anomaly detection (on facial recognition) being performed in 1990 [ 16 , 17 ].…”

“…Machine learning (ML) and deep learning (DL), in particular, are common tools for anomaly detection [ 1 , 2 , 3 , 4 , 5 , 6 ]. With the rapid increase in the number of Internet-connected devices, the growing desire for Internet of Things (IoT) devices in the home, on our person, and in our vehicles, and the transition to smart infrastructure and the Industrial IoT (IIoT), anomaly detection in these devices is critical.…”

Autoscaling in Serverless Computing : Taxonomy and OpenChallenges

“…Anomalies are unexpected events that deviate from the typical pattern of data in cloud computing. Three types of anomalies in the cloud environment have been classified into point anomalies, collective anomalies, and contextual anomalies [72]. Distributed denial of service (DDoS) attacks can cause anomalies in the cloud environment by flooding the system with traffic and preventing legitimate users from accessing shared resources [73].…”

AI - Based Framework for Private Cloud Computing

“…The Reinforcement Learning (RL) method was taught using an Arti cial Neural Network (ANN) to optimize the e ciency and pro tability of private cloud storage services over time. This learned method incorporates a novel approach to converting the merit of each condition into a particular effect [11].…”