Modelling and Design of Pre-Equalizers for a Fully Operational Visible Light Communication System.

Nowadays, Visible Light Communication (VLC) has gained much attention due to the significant advancements in Light Emitting Diode (LED) technology. However, the bandwidth of LEDs is one of the important concerns that limits the transmission rates in a VLC system. In order to eliminate this limitation, various types of equalization methods are employed. Among these, using digital pre-equalizers can be a good choice because of their simple and reusable structure. Therefore, several digital pre-equalizer methods have been proposed for VLC systems in the literature. Yet, there is no study in the literature that examines the implementation of digital pre-equalizers in a realistic VLC system based on the IEEE 802.15.13 standard. Hence, the purpose of this study is to propose digital pre-equalizers for VLC systems based on the IEEE 802.15.13 standard. For this purpose, firstly, a realistic channel model is built by collecting the signal recordings from a real 802.15.13-compliant VLC system. Then, the channel model is integrated into a VLC system modeled in MATLAB. This is followed by the design of two different digital pre-equalizers. Next, simulations are conducted to evaluate their feasibility in terms of the system's BER performance under bandwidth-efficient modulation schemes, such as 64-QAM and 256-QAM. Results show that, although the second pre-equalizer provides lower BERs, its design and implementation might be costly. Nevertheless, the first design can be selected as a low-cost alternative to be used in the VLC system.

An XAI approach for COVID-19 detection using transfer learning with X-ray images.

The coronavirus disease (COVID-19) has continued to cause severe challenges during this unprecedented time, affecting every part of daily life in terms of health, economics, and social development. There is an increasing demand for chest X-ray (CXR) scans, as pneumonia is the primary and vital complication of COVID-19. CXR is widely used as a screening tool for lung-related diseases due to its simple and relatively inexpensive application. However, these scans require expert radiologists to interpret the results for clinical decisions, i.e., diagnosis, treatment, and prognosis. The digitalization of various sectors, including healthcare, has accelerated during the pandemic, with the use and importance of Artificial Intelligence (AI) dramatically increasing. This paper proposes a model using an Explainable Artificial Intelligence (XAI) technique to detect and interpret COVID-19 positive CXR images. We further analyze the impact of COVID-19 positive CXR images using heatmaps. The proposed model leverages transfer learning and data augmentation techniques for faster and more adequate model training. Lung segmentation is applied to enhance the model performance further. We conducted a pre-trained network comparison with the highest classification performance (F1-Score: 98%) using the ResNet model.

Towards robust autonomous driving systems through adversarial test set generation.

Correct environmental perception of objects on the road is vital for the safety of autonomous driving. Making appropriate decisions by the autonomous driving algorithm could be hindered by data perturbations and more recently, by adversarial attacks. We propose an adversarial test input generation approach based on uncertainty to make the machine learning (ML) model more robust against data perturbations and adversarial attacks. Adversarial attacks and uncertain inputs can affect the ML model's performance, which can have severe consequences such as the misclassification of objects on the road by autonomous vehicles, leading to incorrect decision-making. We show that we can obtain more robust ML models for autonomous driving by making a dataset that includes highly-uncertain adversarial test inputs during the re-training phase. We demonstrate an improvement in the accuracy of the robust model by more than 12%, with a notable drop in the uncertainty of the decisions returned by the model. We believe our approach will assist in further developing risk-aware autonomous systems.

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples.

Deep neural network (DNN) architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called ``Adversarial Machine Learning" to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, most of the current research has concentrated on utilising model loss function to craft adversarial examples or to create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the shifted-domain regions where the model has not been trained on. We proposed new attack ideas by exploiting the difficulty of the target model to discriminate between samples drawn from original and shifted versions of the training data distribution by utilizing epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.14%, 82.96% to 90.13% and 89.44% to 91.06% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.

Data augmentation based malware detection using convolutional neural networks.

Due to advancements in malware competencies, cyber-attacks have been broadly observed in the digital world. Cyber-attacks can hit an organization hard by causing several damages such as data breach, financial loss, and reputation loss. Some of the most prominent examples of ransomware attacks in history are WannaCry and Petya, which impacted companies' finances throughout the globe. Both WannaCry and Petya caused operational processes inoperable by targeting critical infrastructure. It is quite impossible for anti-virus applications using traditional signature-based methods to detect this type of malware because they have different characteristics on each contaminated computer. The most important feature of this type of malware is that they change their contents using their mutation engines to create another hash representation of the executable file as they propagate from one computer to another. To overcome this method that attackers use to camouflage malware, we have created three-channel image files of malicious software. Attackers make different variants of the same software because they modify the contents of the malware. In the solution to this problem, we created variants of the images by applying data augmentation methods. This article aims to provide an image augmentation enhanced deep convolutional neural network (CNN) models for detecting malware families in a metamorphic malware environment. The main contributions of the article consist of three components, including image generation from malware samples, image augmentation, and the last one is classifying the malware families by using a CNN model. In the first component, the collected malware samples are converted into binary file to 3-channel images using the windowing technique. The second component of the system create the augmented version of the images, and the last part builds a classification model. This study uses five different deep CNN model for malware family detection. The results obtained by the classifier demonstrate accuracy up to 98%, which is quite satisfactory.

Deep learning based Sequential model for malware analysis using Windows exe API Calls.

Malware development has seen diversity in terms of architecture and features. This advancement in the competencies of malware poses a severe threat and opens new research dimensions in malware detection. This study is focused on metamorphic malware, which is the most advanced member of the malware family. It is quite impossible for anti-virus applications using traditional signature-based methods to detect metamorphic malware, which makes it difficult to classify this type of malware accordingly. Recent research literature about malware detection and classification discusses this issue related to malware behavior. The main goal of this paper is to develop a classification method according to malware types by taking into consideration the behavior of malware. We started this research by developing a new dataset containing API calls made on the windows operating system, which represents the behavior of malicious software. The types of malicious malware included in the dataset are Adware, Backdoor, Downloader, Dropper, spyware, Trojan, Virus, and Worm. The classification method used in this study is LSTM (Long Short-Term Memory), which is a widely used classification method in sequential data. The results obtained by the classifier demonstrate accuracy up to 95% with 0.83 $F_1$-score, which is quite satisfactory. We also run our experiments with binary and multi-class malware datasets to show the classification performance of the LSTM model. Another significant contribution of this research paper is the development of a new dataset for Windows operating systems based on API calls. To the best of our knowledge, there is no such dataset available before our research. The availability of our dataset on GitHub facilitates the research community in the domain of malware detection to benefit and make a further contribution to this domain.