Description

ABSTRACT

This study is on a systematic literature review  of anomaly-based cyber attacks detection for smart homes. Smart homes, leveraging IoT technology to interconnect various devices and appliances to the internet, enable remote monitoring, automation, and control. However, collecting sensitive personal and business data assets renders smart homes a target for cyber attacks. Anomaly detection is a promising approach for identifying malicious behavior in smart homes. Yet, the current literature primarily discusses IoT-related cyber attacks and gives limited attention to detecting anomalies specific to the smart home context. Furthermore, there is a lack of data sets that accurately represent the complexity inherent in a smart home environment in terms of users with varying levels of expertise and diverse, evolving types of devices. Therefore, this paper presents a systematic literature review (SLR) that focuses on using anomaly detection to identify cyber attacks in smart home environments. The SLR includes an adapted taxonomy that classifies existing anomaly detection methods and a critical analysis of the current state of knowledge and future research challenges.

TABLE OF CONTENTS

Cover page/Title page

Certification page

Executive summary

CHAPTER ONE

• Introduction
  • Background of the Study
  • Problem Statement
  • Aim and Objectives
  • Scope of the Study
  • significance of the Study

CHAPTER TWO

• Literature Review
  • Smart homes
  • Threats taxonomies
  • Cyber attacks

CHAPTER THREE

• Anomaly detection

3.2 The review process

• Planning phase
• Review protocol
• Smart home features
• Privacy
• Smart home data sets
• Changing environment
• Zero-days cyber attacks

3.10         Conclusion

Reference

CHAPTER ONE

1.0                                                               Introduction

2.1                                                   Background of the study

Digital assets protection from cyber attacks is a significant concern as society is becoming digital. These assets can include operational data, Personally Identifiable Information(PII), or strategic information; and are generated, stored, and transferred in organizations, homes, and personal devices. Particularly, the protection of homes has taken relevance with the rise of telecommuting, and smart homes must receive special attention (Chatterjee et al., 2022).

Anomaly-based detection system (ADS) demonstrates promising results in IoT security, but implementing these solutions in the context of smart homes is a significant challenge. Because these environments involve many user-device interactions (Chatterjee et al., 2022). Moreover, the heterogeneity of these environments makes it difficult to create anomaly-based  detection system that can be implemented in any smart home. Indeed, user behavior can change overtime, and new occupants can move into a home. In addition, the devices, model brands, communication systems, protocols, and digital assets in each residence can vary considerably. A smart home environment has very high risks. Therefore, it is necessary to have defense systems that can adapt to the environment and detect both old and new cyber attacks without requiring a model update.

Concepts of what a smart home is and the many types of cyber attacks that can affect these environments can be found in the literature and will be covered in further detail below. However, no taxonomies on anomaly detection approaches used by researchers in the field have been identified and studied in this work.

1.2      Statement of the problem

Smart homes are an attractive target for cyber criminals due to the lack of user technical knowledge, insecure Internet of Things (IoT) devices, inadequate configurations, poor implementation of controls, and the high value of the digital assets involved. The IoT industry has grown exponentially; it is expected to grow to 48 billion connected devices by 2023. However, new vulnerabilities have been continuously discovered and threats have emerged. Indeed, everyday new cyber attacks (zero-day attacks) exploit these weaknesses with enormous potential damage (Dahlqvist et al., 2019).

Anomaly-based Detection Systems (ADS) are a promising approach to detect unknown cyber attacks. ADS is a complex field that attempts to distinguish between abnormal and normal behavior. These systems work by establishing a baseline of normal behavior and they continuously monitor the network or device to flag suspicious deviations. Due to the changing behavior of users and cyber attackers, the most difficult aspect of this field is keeping the models up-to-date(Singh et al., 2019).

1.3      Aim and objectives of the study

The aim of this seminar is to carry out a systematic literature review of an anomaly-based cyber attacks detection for smart homes. The objectives of the seminar are:

1. To study different means of providing a security to a smart home
2. To have full knowledge of anomaly-based cyber attacks detection
3. To study different ways of providing an up-to-date security in a smart home.

1.4      Scope of the study

In this seminar, a systematic literature review (SLR) is developed, which requires a review of several concepts and taxonomies for the selection and categorization of different works.

1.5      Significance of the study

This study will serve as a means of understanding different means of providing an up-to-date security in a smart home.

The study will also serve as a means of reviewing different smart home security system thereby providing a deep knowledge to the reader and also to the student involved.

This seminar will also serve as an avenue of making recommendation on how cyber security can be improved.

3.1    Conclusion

Research into anomaly-based cyber attack detection systems has increased significantly in recent years. Anomaly-based cyber attack detection systems has excellent potential to identify different types of cyber attacks in a smart home context. Furthermore, with the development of telecommuting, detecting known and unknown cyber attacks targeted at the smart home is relevant and can prevent several cyber threats. This paper has presented a careful study of there center search in anomaly-based cyber attack detection systems on intelligent home environments and its detection, placement, and validation strategies, source of features, data sets, type of anomaly data, evaluation metrics, and open issues. Also, existing taxonomies for anomaly detection and machine learning had to be changed to fit the cyber attack detection methods in the SLR-selected papers. New studies on smart home intrusion detection systems must consider the specific characteristics of these environments: multiple in habitats, changing behavior overtime, devices interacting with each other, configuration and management of devices in the cloud through mobile devices, a lack of knowledge of the application of security measures ,among others. Also, users of smart homes will not care if the IDS can find the most recent attacks or if the firm ware on their home devices is up to date, so IDS and related architectures must consider these things