Cyberattacks always remain the major threats and challenging issues in the modern digital world. With the increase in the number of internet of things (IoT) devices, security challenges in these devices, such as lack of encryption, malware, ransomware, and IoT botnets, leave the devices vulnerable to attackers that can access and manipulate the important data, threaten the system, and demand ransom. The lessons from the earlier experiences of cyberattacks demand the development of the best-practices benchmark of cybersecurity, especially in modern Smart Environments. In this study, we propose an approach with a framework to discover malware attacks by using artificial intelligence (AI) methods to cover diverse and distributed scenarios. The new method facilitates proactively tracking network traffic data to detect malware and attacks in the IoT ecosystem. Moreover, the novel approach makes Smart Environments more secure and aware of possible future threats. The performance and concurrency testing of the deep neural network (DNN) model deployed in IoT devices are computed to validate the possibility of in-production implementation. By deploying the DNN model on two selected IoT gateways, we observed very promising results, with less than 30 kb/s increase in network bandwidth on average, and just a 2% increase in CPU consumption. Similarly, we noticed minimal physical memory and power consumption, with 0.42 GB and 0.2 GB memory usage for NVIDIA Jetson and Raspberry Pi devices, respectively, and an average 13.5% increase in power consumption per device with the deployed model. The ML models were able to demonstrate nearly 93% of detection accuracy and 92% f1-score on both utilized datasets. The result of the models shows that our framework detects malware and attacks in Smart Environments accurately and efficiently.

For the past few years, the Internet of Things (IoT) technology continues to not only gain popularity and importance, but also witnesses the true realization of everything being smart. With the advent of the concept of smart everything , IoT has emerged as an area of great potential and incredible growth. An IoT ecosystem centers around innovation perspective which is considered as its fundamental core. Accordingly, IoT enabling technologies such as hardware and software platforms as well as standards become the core of the IoT ecosystem. However, any large-scale technological integration such as the IoT development poses the challenge to ensure secure data transmission. Perhaps, the ubiquitous and the resource-constrained nature of IoT devices and the sensitive and private data being generated by IoT systems make them highly vulnerable to physical and cyber threats. In this paper, we re-define an IoT ecosystem from the core technologies view point. We propose a modified three layer IoT architecture by dividing the perception layer into elementary blocks based on their attributed functions. Enabling technologies, attacks and security countermeasures are classified under each layer of the proposed architecture. Additionally, to give the readers a broader perspective of the research area, we discuss the role of various state-of-the-art emerging technologies in the IoT security. We present the security aspects of the most prominent standards and other recently developed technologies for IoT which might have the potential to form the yet undefined IoT architecture. Among the technologies presented in this article, we give a special interest to one recent technology in IoT domain. This technology is named IQRF that stands for Intelligent Connectivity using Radio Frequency. It is an emerging technology for wireless packet-oriented communication that operates in sub-GHz ISM band (868 Mhz) and which is intended for general use where wireless connectivity is needed, either in a mesh network or point-to-point (P2P) configuration. We also highlighted the security aspects implemented in this technology and we compare it with the other already known technologies. Moreover, a detailed discussion on the possible attacks is presented. These attacks are projected on the IoT technologies presented in this article including IQRF. In addition, lightweight security solutions, implemented in these technologies, to counter these threats in the proposed IoT ecosystem architecture are also presented. Lastly, we summarize the survey by listing out some common challenges and the future research directions in this field.

Growing number of Smart Applications in recent years bring a completely new landscape of cyber-attacks and exploitation scenario that have not been seen in wild before. Devices in Edge commonly have very limited computational resources and corresponding power source reducing the number of conventional cybersecurity measures available for deployment. This also puts strict requirements on how the signatures of malicious actions can be updated and actualized. It has been proved efficiency of Machine Learning models, Neural Networks in particular, in multiple tasks related to cybersecurity due to the high-abstract precise models and training from historical data. However, when it comes to the devices in Edge, it is clear that the extensive training of the model is not possible, while testing of new unseen data can be successfully done. In addition to the conventional understanding of off-line and on-line model training, this contribution looks into how the Machine Learning can be successfully deployed on IoT while putting unnecessary computations off-chip through parameters transfer over MQTT network, reducing computational footprint on microcontrollers. We believe that proposed approach will be beneficial for many applications in resource-constrained environment.

The Internet of Things (IoT) is omnipresent, exposing a large number of devices that often lack security controls to the public Internet. In the modern world, many everyday processes depend on these devices, and their service outage could lead to catastrophic consequences. There are many Deep Packet Inspection (DPI) based intrusion detection systems (IDS). However, their linear computational complexity induced by the event-driven nature poses a power-demanding obstacle in resource-constrained IoT environments. In this paper, we shift away from the traditional IDS as we introduce a novel and lightweight framework, relying on a time-driven algorithm to detect Distributed Denial of Service (DDoS) attacks by employing Machine Learning (ML) algorithms leveraging the newly engineered features containing system and network utilization information. These features are periodically generated, and there are only ten of them, resulting in a low and constant algorithmic complexity. Moreover, we leverage IoT-specific patterns to detect malicious traffic as we argue that each Denial of Service (DoS) attack leaves a unique fingerprint in the proposed set of features. We construct a dataset by launching some of the most prevalent DoS attacks against an IoT device, and we demonstrate the effectiveness of our approach with high accuracy. The results show that standalone IoT devices can detect and classify DoS and, therefore, arguably, DDoS attacks against them at a low computational cost with a deterministic delay.