Machine learning algorithms represent the intelligence that controls many information systems and applications around us. As such, they are targeted by attackers to impact their decisions. Text created by machine learning algorithms has many types of applications, some of which can be considered malicious especially if there is an intention to present machine-generated text as human-generated. In this paper, we surveyed major subjects in adversarial machine learning for text processing applications. Unlike adversarial machine learning in images, text problems and applications are heterogeneous. Thus, each problem can have its own challenges. We focused on some of the evolving research areas such as: malicious versus genuine text generation metrics, defense against adversarial attacks, and text generation models and algorithms. Our study showed that as applications of text generation will continue to grow in the near future, the type and nature of attacks on those applications and their machine learning algorithms will continue to grow as well. Literature survey indicated an increasing trend in using pre-trained models in machine learning. Word/sentence embedding models and transformers are examples of those pre-trained models. Adversarial models may utilize same or similar pre-trained models as well. In another trend related to text generation models, literature showed effort to develop universal text perturbations to be used in both black-and white-box attack settings. Literature showed also using conditional GANs to create latent representation for writing types. This usage will allow for a seamless lexical and grammatical transition between various writing styles. In text generation metrics, research trends showed developing successful automated or semi-automated assessment metrics that may include human judgement. Literature showed also research trends of designing and developing new memory models that increase performance and memory utilization efficiency without validating real-time constraints. Many research efforts evaluate different defense model approaches and algorithms. Researchers evaluated different types of targeted attacks, and methods to distinguish human versus machine generated text.

Recently, unmanned aerial vehicles (UAVs) have been used as flying base stations (BSs) to take advantage of line‐of‐sight (LOS) connectivity and efficiently enable fifth‐generation (5G) and cellular network coverage and data rates. On the other hand, nonorthogonal multiple access (NOMA) is a promising technique to help achieve unprecedented requirements by simultaneously allowing multiple users to send data over the same resource block. In this paper, we study a UAV‐enabled uplink NOMA network, where the UAV collects data from ground users while flying at a certain altitude. Unlike all existing work on this topic, this study consists of two stages. In the first stage, we use the well‐known Particle Swarm Optimization (PSO) algorithm, which is a metaheuristic algorithm, to deploy the UAV in 3D space, so that the users’ sum pathlosses are minimized. In the second stage, we investigate the user pairing problem and propose a dynamic power allocation technique for determining the user’s power allocation coefficients, as well as a closed‐form equation for the ergodic sum‐rate. Results show our PSO‐based algorithm prevailing over the Genetic Algorithm (GA) and random deployment methods. The proposed dynamic power allocation strategy maximizes the network’s ergodic sum‐rate and outperforms the fixed power allocation strategy. Additionally, the results reveal that the best pairing scheme is the one that keeps uniform channel gain difference in the same pair.

Unmanned aerial vehicles (UAVs), also named as drones, have become a modern model to provide a quick wireless communication infrastructure. They have been used when conventional base stations’ capacity is suffering in some extreme cases such as congestion inside the cell or a special event. This paper proposes an efficient three‐dimension (3D) placement of a single UAV‐assisted wireless network in such cases. Our proposed model assists the ground base station (GBS) using the UAV to serve arbitrary distributed users considering the impact of the obstacle blockage over the well‐known air‐to‐ground (A2G) path model. This work is aimed at optimizing the percentage of available bandwidth that must be provided to the UAV in order to maximize the number of served users. In addition, it finds the 3D placement of the UAV base station (UAVBS) that maximizes the number of served users, each with maximum quality‐of‐service (QoS). The exhaustive search and particle swarm optimization (PSO) algorithms are used to find the problem’s solution.

Accurate energy consumption prediction in commercial buildings is a challenging research task. Energy prediction plays a crucial role in energy efficiency, management, planning, sustainability, risk management, diagnosis, and demand response. Although many studies have been conducted on building energy predictions, the impact of occupancy on energy prediction models for office-type commercial buildings remains insufficiently explored, despite its potential to improve energy efficiency by 20%. This study investigates energy prediction using a Long Short-Term Memory (LSTM) model that incorporates time-series power consumption data and considers occupancy. A real-world dataset containing the per-minute electricity consumption of various appliances in an office building in Houston, TX, USA, is utilized. The proposed machine learning models forecast future energy consumption based on hourly, 3-hourly, daily, and quarterly predictions for individual appliances and total energy usage. The model’s performance is evaluated using the following three metrics: Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results demonstrate the superiority of the proposed system.

Due to natural disasters, unmanned aerial vehicles (UAVs) can be deployed as aerial wireless base stations when conventional cellular networks are out of service. They can also supplement the mobile ground station to provide wireless devices with improved coverage and faster data rates. Cells on wheels (CoWs) can also be utilized to provide enhanced wireless coverage for short‐term demands. In this paper, a single CoW cooperates with a single UAV in order to provide maximum wireless coverage to ground users. The optimization problem is formulated to find the following: (1) the optimal 2D placement of the CoW, (2) the optimal 3D placement of the UAV, (3) the optimal bandwidth allocation, (4) the percentage of the available bandwidth that must be provided to the CoW and UAV, and (5) the priority of wireless coverage; which maximizes the number of covered users. We utilize the exhaustive search (ES) and particle swarm optimization (PSO) algorithms to solve the optimization problem. The effectiveness of the proposed algorithms is validated using simulation results.

The breakthroughs in Machine learning and deep neural networks have revolutionized the handling of critical practical challenges, achieving state-of-the-art performance in various computer vision tasks. Notably, the application of deep neural networks in optical character recognition (OCR) has significantly enhanced the performance of OCR systems, making them a pivotal preprocessing component in text analysis pipelines for crucial applications such as license plate recognition (LPR) systems, where the efficiency of OCR is paramount. However, despite the advancements, the integration of deep neural networks in OCR introduces inherent security vulnerabilities, particularly susceptibility to adversarial examples. Adversarial examples in LPR systems are crafted by introducing perturbations to original license plate images, which can effectively compromise the integrity of the license plate recognition process, leading to erroneous license plate number identification. Given that the primary goal of OCR in this context is to accurately recognize license plate numbers, even a single misinterpreted character can significantly impact the overall performance of the LPR system. The vulnerability of LPR systems to adversarial attacks underscores the urgent need to address the security weaknesses inherited from deep neural networks. In response to these challenges, the exploration of alternative defense mechanisms, such as image denoising and in-painting, presents a compelling approach to bolstering the resilience of LPR systems against adversarial attacks. By prioritizing practical implementation and integration of image denoising and inpainting techniques align with the operational requirements of real-world LPR systems. These methods can be seamlessly integrated into existing pipelines, offering pragmatic and accessible means of enhancing security without imposing significant computational overhead. By embracing a multi-faceted approach that combines the strengths of traditional image processing techniques, the research endeavors to develop comprehensive and versatile defense strategies tailored to the specific vulnerabilities and requirements of LPR systems. This holistic approach aims to fortify LPR systems against adversarial threats, thereby fostering increased trust and reliability in the deployment of OCR and LPR technologies across various domains and applications.