The future Internet of Things (IoT) will have a deep economical, commercial and social impact on our lives. The participating nodes in IoT networks are usually resource-constrained, which makes them luring targets for cyber attacks. In this regard, extensive efforts have been made to address the security and privacy issues in IoT networks primarily through traditional cryptographic approaches. However, the unique characteristics of IoT nodes render the existing solutions insufficient to encompass the entire security spectrum of the IoT networks. Machine Learning (ML) and Deep Learning (DL) techniques, which are able to provide embedded intelligence in the IoT devices and networks, can be leveraged to cope with different security problems. In this paper, we systematically review the security requirements, attack vectors, and the current security solutions for the IoT networks. We then shed light on the gaps in these security solutions that call for ML and DL approaches. Finally, we discuss in detail the existing ML and DL solutions for addressing different security problems in IoT networks. We also discuss several future research directions for ML- and DL-based IoT security.

Machine Learning in IoT Security: Current Solutions and Future Challenges

The Internet of Things, abbreviated as IoT, is a new networking paradigm composed of wireless and wired networks, geographically distributed and interconnected by a “secured” backbone, essentially, the Internet. It connects billions of heterogeneous devices, called Things, using different communication technologies and provides end-users, all over the world, with a variety of smart applications. IoT constitutes a new evolution for the Internet in terms of diversity, size, and applications. It also invites cybercriminals who exploit IoT infrastructures to conduct large scale, distributed, and devastating cyberattacks that may have serious consequences. The security of IoT infrastructures strongly depends on the security of its wired and wireless infrastructures. Still, the wireless infrastructures are thought to be the most outspread, important, and vulnerable part of IoT. To achieve the security goals in the wireless infrastructures of IoT, it is crucial to have a comprehensive understanding of IoT attacks, their classification, and security solutions in such infrastructures. In this paper, we provide a survey of attacks related to the wireless infrastructures of IoT in general, and to the most used short-range wireless communication technologies in the resource-constrained part of IoT in particular. Namely, we consider Wi-Fi, Bluetooth, ZigBee, and RFID wireless communication technologies. The paper also provides a taxonomy of these attacks based on a security service-based attack classification and discusses existing security defenses and mechanisms that mitigate certain attacks as well as the limitations of these security mechanisms.

/pdf/attacks-and-defenses-in-short-range-wireless-technologies-1qp83e01b4.pdf

Attacks and Defenses in Short-Range Wireless Technologies for IoT

The escalated growth of the Internet of Things (IoT) has started to reform and reshape our lives. The deployment of a large number of objects adhered to the internet has unlocked the vision of the smart world around us, thereby paving a road towards automation and humongous data generation and collection. This automation and continuous explosion of personal and professional information to the digital world provides a potent ground to the adversaries to perform numerous cyber-attacks, thus making security in IoT a sizeable concern. Hence, timely detection and prevention of such threats are pre-requisites to prevent serious consequences. The survey conducted provides a brief insight into the technology with prime attention towards the various attacks and anomalies and their detection based on the intelligent intrusion detection system (IDS). The comprehensive look-over presented in this paper provides an in-depth analysis and assessment of diverse machine learning and deep learning-based network intrusion detection system (NIDS). Additionally, a case study of healthcare in IoT is presented. The study depicts the architecture, security, and privacy issues and application of learning paradigms in this sector. The research assessment is finally concluded by listing the results derived from the literature. Additionally, the paper discusses numerous research challenges to allow further rectifications in the approaches to deal with unusual complications.

Internet of Things: Evolution, Concerns and Security Challenges

Survey on sybil attack defense mechanisms in wireless ad hoc networks

Design of intrusion detection and prevention scheme for improving MANET security, with considered energy efficiency, detection rate, delay, and false positive rate are major research issues. Most of the existing solutions have suffered to obtain accurate detection rate in minimal time execution and energy consumption. In this work we proposed a Smart approach for intrusion detection and prevention system (SA-IDPS) to mitigate attacks in MANET by machine learning methods. Initially, mobile users are registered in Trusted Authority using One Way Hash Chain Function. Each mobile user submits their following information to verify authentication: finger vein biometric, user id, and latitude and longitude. Intrusion detection is executed using four entities: Packet Analyzer, Preprocessing Unit, Feature Extraction Unit and Classification Unit. In packet analyzer, we verify whether any attack pattern is found or not. It is implemented using Type 2 Fuzzy Controller which considers information from packet header. In preprocessing unit, logarithmic normalization and encoding schemes are considered, which is time series and suitable for any application. In feature extraction unit, Mutual Information is used where we extracts optimum set of features for packets classification. In classification unit, Bootstrapped Optimistic Algorithm for Tree Construction with Artificial Neural Network is used for packets classification, which classifies packets five classes: DoS, Probe, U2R, R2L, and Anomaly, and then Association Rule Tree are used to classify whether the attack is Frequent or Rare. In this case, historical table is used for packets classification. Finally, experiments are conducted and tested for evaluating the performance of proposed SA-IDPS scheme in terms of Detection Rate (%), False Positive Rate (%), Detection Delay (s), and Energy Consumption (J).

A Smart Approach for Intrusion Detection and Prevention System in Mobile Ad Hoc Networks Against Security Attacks

Nowadays, the study of the security of IoT has caught many attentions of researchers. Improving our world to be a better environment building a city of dreams which is called smart city is a trend field of research. In this context, objects will be connected to the Internet interacting with each other making the world more smarter. The variety of networks building makes the IoT vulnerable. Smart home, smart grid, Smart transport, WSN, UASN, UWASN, etc make our lives more easier by offering intelligent services that save time and effort. However, each network is exposed to some attacks that can disturb its performance. In this paper, we present a classification of attacks from various networks involved in IoT. This classification distinguish common and specific attacks from each network and use some criteria like the security attributes, congestion, disturbance. Also, some existing security solutions are presented in details in order to expose the security requirements to protect IoT.

A survey on attacks in Internet of Things based networks

The vulnerabilities of Mobile Ad Hoc Networks (MANETs) are subject of numerous kinds of attacks. Many classification schemas and taxonomies of MANET attacks have been proposed in the literature in order to understand the technique of the attack as well as the behavior of attackers. The following paper presents a new classification of attacks in MANET. We distinguish three leading classes of attacks in MANET: In the first class, we make a large analysis of attacks according to the OSI models. In the second, the classification is performed according to the principal main factors leading to this attack such as sources of attacks, attacker behavior and involved nodes. In the third, we performed the analysis according to the target service chosen by the attacker.

A survey of attacks in mobile ad hoc networks

Privacy Preservation and Drone Authentication Using ID-Based Signcryption.

This paper proposes a system for the prevention and the detection of Sybil attacks in Military Wireless Sensor networks (MWSNs). The identification of Sybil attacker is based on two types of authentication techniques. The first is based on the use of RFID tags embedded in Soldiers to authenticate them and get certificates. The second is based on the use of those certificates by soldiers to authenticate them to their neighbors. The solution prevents Sybil attacks by identifying soldiers that are using two valid certificates at the same time. The heartbeat of the soldier is used to enforce the authentication of soldiers and the privacy of soldiers is preserved where the team leaders of soldiers are the only entities that are able to detect the Sybil attack know about the real identity of each soldier.

Bayrem Triki

Papers

A survey on attacks in Internet of Things based networks

A survey of attacks in mobile ad hoc networks

Privacy Preservation and Drone Authentication Using ID-Based Signcryption.

An RFID based System for the detection of Sybil attack in Military Wireless Sensor networks

Anomaly-based Behavioral Detection in Mobile Ad-Hoc Networks