<span id="docs-internal-guid-345787a5-7fff-6d93-73dd-f99a81d82f61"><span>The massive network traffic data between connected devices in the internet of things have taken a big challenge to many traditional intrusion detection systems (IDS) to find probable security breaches. However, security attacks lean towards unpredictability. There are numerous difficulties to build up adaptable and powerful IDS for IoT in order to avoid false alerts and ensure a high recognition precision against attacks, especially with the rising of Botnet attacks. These attacks can even make harmless devices becoming zombies that send malicious traffic and disturb the network. In this paper, we propose a new IDS solution, baptized BotIDS, based on deep learning convolutional neural networks (CNN). The main interest of this work is to design, implement and test our IDS against some well-known Botnet attacks using a specific Bot-IoT dataset. Compared to other deep learning techniques, such as simple RNN, LSTM and GRU, the obtained results of our BotIDS are promising with 99.94% in validation accuracy, 0.58% in validation loss, and the prediction execution time is less than 0.34 ms.</span></span>

<p>Deep learning (DL) models are nowadays broadly applied and have shown outstanding performance in a variety of fields, including our focus topic of "IoTcybersecurity". Deep learning-based intrusion detection system (DL-IDS) models are more fixated and depended on the trained dataset. This poses a problem for these DL-IDS, especially with the known mutation and behavior changes of attacks, which can render them undetected. As a result, the DL-IDShas become outdated. In this work, we present a solution for updating DL-ID Semploying a transfer learning technique that allows us to retrain and fine-tune pre-trained models on small datasets with new attack behaviors. In our experiments, we built CNN-based IDS on the Bot-IoT dataset and updated it on small data from a new dataset named TON-IoT. We obtained promising results in multiple metrics regarding the detection rate and the training between the initial training for the original model and the updated one, in the matter of detecting new attacks behaviors and improving the detection rate for some classes by overcoming the lack of their labeled data.</p>

No abstract

<span lang="EN-US">The impact of wildfires, even following the fire's extinguishment, continues to affect harmfully public health and prosperity. Wildfires are becoming increasingly frequent and severe, and make the world's biodiversity in a growing serious danger. The fires are responsible for negative economic consequences for individuals, corporations, and authorities. Researchers are developing new approaches for detecting and monitoring wildfires, that make use of advances in computer vision, machine learning, and remote sensing technologies. IoT sensors help to improve the efficiency of detecting active forest fires. In this paper, we propose a novel approach for predicting wildfires, based on machine learning. It uses a regression model that we train over NASA's fire information for resource management system (FIRMS) dataset to predict fire radiant power in megawatts. The analysis of the obtained simulation results (more than 99% in the R2 metric) shows that the ensemble learning model is an effective method for predicting wildfires using an IoT device equipped with several sensors that could potentially collect the same data as the FIRMS dataset, such as smart cameras or drones.</span>

No abstract

The Internet of Things (IoT) is now present in every domain from applications in smart homes, Smart Cities, Industrial Internet of Things (IIoT), such as e-Health, and beyond. The wide use of Internet of Things is making its security a real concern. Techniques based on artificial intelligence (AI) and its subsets machine learning (ML) and deep learning (DL) are commonly used to develop a secure Intrusion Detection System (IDS) for IoT. Researchers and industrialists are commonly using commercial Internet of Things devices, broadly available on the market. In this paper, we present an analysis of the possibility to deploy a Deep Learning-Based Host-Intrusion Detection System (DL-HIDS) on some specific commercial IoT devices. We performed multiple optimizations regarding the types of our used devices to meet their limited hardware specifications. In our conducted analysis, we consider such criteria, as memory consumption and inference timing (attacks prediction timing), to conclude which model fits better to our proposed lightweight DL-HIDS for each studied device, and to anticipate about which IDS we must generate and expectedly deploy based on the characteristics of the devices we possess. The paper also discusses the proposed methodology for such deployment in a real IoT environment. The obtained results about the implementation of our DL-HIDS on different considered devices (up to 99.74% in accuracy and an inference of not more of 1µs for attacks prediction) are promising and prove that we can manage to install a suited IDS for each device, but it should be minutiously supported by a central IDS in fog or cloud layers.

Machine learning (ML) and deep learning (DL) have achieved amazing progress in diverse disciplines. One of the most efficient approaches is unsupervised learning (UL), a sort of algorithms for analyzing and clustering unlabeled data; it allows identifying hidden patterns or performing data clustering over provided data without the need for human involvement. There is no prior knowledge of actual abnormalities when using UL methods in anomaly detection (AD); hence, a DL-intrusion detection system (IDS)- based on AD depends intensely on their assumption about the distribution of anomalies. In this paper, we propose a novel unsupervised AD Host-IDS for internet of things (IoT) based on adversarial training architecture using the generative adversarial network (GAN). Our proposed IDS, called “EdgeIDS”, targets mostly IoT devices because of their limited functionality; IoT devices send and receive only specific data, not like traditional devices, such as servers or computers that exchange a wide range of data. We benchmarked our proposed “EdgeIDS” on the message queuing telemetry transport (MQTTset) dataset with five attack types, and our obtained results are promising, up to 0.99 in the ROC-AUC metric, and to just 0.035 in the ROC-EER metric. Our proposed technique could be a solution for detecting cyber abnormalities in the IoT.

Many solar plants have been installed globally, and they must be continuously protected and supervised to ensure their safety and reliability. Photovoltaic plants are susceptible to many defects and failures, and fault detection technology is used to protect and isolate them. Despite numerous inter-national standards, invisible photovoltaic defects continue to cause major is-sues. As a result, smart technologies like AI (Artificial Intelligence) and IoT are being developed for remote sensing, problem detection, and diagnosis of photovoltaic systems. Solar plants generate not only green electricity but also a lot of data, such as power output. With AI, a clear picture of electricity yields should be possible. The output of entire solar parks could be monitored and analyzed. The AI could also detect malfunctions within a solar park, according to the research. This would speed up and simplify maintenance work. Deep learning (DL) and IoT applications for photovoltaic plants are discussed. The most advanced techniques, such as DL, are discussed in terms of precision and accuracy. Incorporating DL and IoT approaches for fault detection and diagnosis into simple hardware, such as low-cost chips, maybe cost-effective and technically feasible for photovoltaic facilities located in remote locations.