Internet of Things: A survey on machine learning-based intrusion detection approaches

The world is resorting to the Internet of Things (IoT) for ease of control and monitoring of smart devices. The ubiquitous use of IoT ranges from industrial control systems (ICS) to e-Health, e-Commerce, smart cities, supply chain management, smart cars, cyber physical systems (CPS), and a lot more. Such reliance on IoT is resulting in a significant amount of data to be generated, collected, processed, and analyzed. The big data analytics is no doubt beneficial for business development. However, at the same time, numerous threats to the availability and privacy of the user data, message, and device integrity, the vulnerability of IoT devices to malware attacks and the risk of physical compromise of devices pose a significant danger to the sustenance of IoT. This paper thus endeavors to highlight most of the known threats at various layers of the IoT architecture with a focus on the anatomy of malware attacks. We present a detailed attack methodology adopted by some of the most successful malware attacks on IoT, including ICS and CPS. We also deduce an attack strategy of a distributed denial of service attack through IoT botnet followed by requisite security measures. In the end, we propose a composite guideline for the development of an IoT security framework based on industry best practices and also highlight lessons learned, pitfalls and some open research challenges.

/pdf/anatomy-of-threats-to-the-internet-of-things-mpzk1hi6sq.pdf

Anatomy of Threats to the Internet of Things

A survey on internet of vehicles: Applications, security issues & solutions

Intelligent Transportation Systems (ITS), especially Autonomous Vehicles (AVs), are vulnerable to security and safety issues that threaten the lives of the people. Unlike manual vehicles, the security of communications and computing components of AVs can be compromised using advanced hacking techniques, thus barring AVs from the effective use in our routine lives. Once manual vehicles are connected to the Internet, called the Internet of Vehicles (IoVs), it would be exploited by cyber-attacks, like denial of service, sniffing, distributed denial of service, spoofing and replay attacks. In this article, we present a deep learning-based Intrusion Detection System (IDS) for ITS, in particular, to discover suspicious network activity of In-Vehicles Networks (IVN), vehicles to vehicles (V2V) communications and vehicles to infrastructure (V2I) networks. A Deep Learning architecture-based Long-Short Term Memory (LSTM) autoencoder algorithm is designed to recognize intrusive events from the central network gateways of AVs. The proposed IDS is evaluated using two benchmark datasets, i.e., the car hacking dataset for in-vehicle communications and the UNSW-NB15 dataset for external network communications. The experimental results demonstrated that our proposed system achieved over a 99% accuracy for detecting all types of attacks on the car hacking dataset and a 98% accuracy on the UNSW-NB15 dataset, outperforming other eight intrusion detection techniques.

Novel Deep Learning-Enabled LSTM Autoencoder Architecture for Discovering Anomalous Events From Intelligent Transportation Systems

Attacks and defences on intelligent connected vehicles: a survey

As a typical application of Internet of Things (IoT) in the field of transportation, Internet of Vehicles (IoV) aims at achieving an integrated intelligent transportation system to enhance traffics efficiency, avoid accidents, ensure road safety, and improve driving experiences by using new IoT technologies. Different from other Internet, it is characterized by dynamic topological structures, huge network scale, non-uniform distribution of nodes, and mobile limitation. Due to these characteristics, IoV systems face various types of attacks, such as authentication and identification attacks, availability attacks, confidentiality attacks, routing attacks, data authenticity attacks, etc., which result in several challenging requirements in security and privacy. Many security scientists made numerous efforts to ensure the security and privacy for the Internet of Vehicles in recent years. This paper aims to review the advances on issues of security and privacy in IoV, including security and privacy requirements, attack types, and the relevant solutions, and discuss challenges and future trends in this area.

Attacks and countermeasures in the internet of vehicles

The impact of COVID-19 on SMEs in China: Textual analysis and empirical evidence

SMEs in China always face financing constraints and hardly obtain bank loans under unsound financing system due to the information asymmetry, while thousands of SMEs have contributed greatly to Chinese economic development in the last decades. Credit reporting has been verified to be an effective way to lower information asymmetry. However, existed credit reporting systems for SMEs can not meet the development of SMEs and provide enough information to the financial institutions in China. This paper introduces an active and dynamic credit reporting framework based on Big data and Blockchain for SMEs. The framework is composed of five modules, including credit data acquisition, authentication, evaluation, reporting, and interaction. And it features in capturing diversified data online, conducting evaluation and analysis in real time, generating online credit reports for users automatically, and providing an effective way for different entities to interact. A case study from a real credit evaluation company is also proposed finally to show the proposed framework.

An active and dynamic credit reporting system for SMEs in China

SMEs (Small and Medium-size Enterprises) in China always face financing constraints and hardly obtain bank loans under unsound financing system. In external f Academic literature has shown that widespread information asymmetry may prevent the efficient allocation of lending, leading to credit rationing. Currently, most credit reporting, models for SMEs in China are primarily based on hard information about the enterprises and their owners but lack comprehensive evaluation based on the combination with soft information. To bridge the gap for SMEs, we propose a novel big-data-driven credit reporting framework which presents a new credit reporting system by including big data in business, finance, and social networks. The proposed approach features in capturing diversified data online, conducting evaluation and analysis in real-time, and automatically generating online credit reports for SMEs, banks, and government. It also provides an efficient interactive way for SMEs to check credit reports online.

A Novel Big-Data-Driven Credit Reporting Framework for SMEs in China

We investigate how asset prices and trading behaviour are impacted by the structure and framing of incentives, using a lab experiment. Subjects buy and sell a high-risk asset, a low-risk asset, and riskless cash over 10 rounds. We vary, between-subjects, the incentive scheme (relative versus absolute performance), and how the variable component of incentives is framed (bonus versus penalty), while holding constant the convexity of incentives. Both relative-performance (tournament) incentives and penalty framing are associated with significant increases in the price of the high-risk asset, relative to either its fundamental value or to the price of the low-risk asset. Additional analysis shows significant gender differences in trading behaviour and performance, and evidence that the two may be connected. 

Xuegang Cui

Papers

Attacks and countermeasures in the internet of vehicles

The impact of COVID-19 on SMEs in China: Textual analysis and empirical evidence

An active and dynamic credit reporting system for SMEs in China

A Novel Big-Data-Driven Credit Reporting Framework for SMEs in China

Incentive schemes, framing, and market behaviour: Evidence from an asset-market experiment