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.

Dynamic features applications present new obstacles for the selection of streaming features. The dynamic features applications have various characteristics: a) features are processed sequentially while the number of instances is fixed; and b) the feature space does not exist in advance. For example, in a text classification task for spam detection, new features (e.g. words) are dynamically generated and therefore need to be mined to filter out the spams rather than waiting for all features to be collected in order to do so. Traditional feature selection methods, which are not designed for streaming features applications, cannot be used in such an environment, as they require the full feature space in advance in order to statistically determine the representative features. Existing methods that address feature selection in dynamic features applications require the class labels in order to select the representative features. However, most of the real-life data is unlabeled and it is costly to apply manual labeling. In this paper, an efficient unsupervised features selection method is proposed for streaming features applications where the number of features increases while the number of instances remains fixed. In particular, unsupervised Feature Selection for Dynamic Features (UFSSF) is developed to determine the representative streaming features without requiring prior knowledge about data class labels or representative features. The UFSSF extends the k-mean clustering to cumulatively determine whether the newly-arrived feature can be selected as a representative streaming feature, or discarded. Experimental results show significant accuracy results and efficient execution time compared to those of other benchmark methods.

Ransomware has appeared to be the most damaging and devastating type of malware attack in any cyber physical system. The resilience of a web browser to deal with the malware attack is of significance importance, however, evaluating the performance of a browser to tackle these attacks is a challenging task. Due to various automation techniques, web applications can be tested without human intervention. Technologies such as Junit, Chakram, and Selenium are useful in automated testing but the problem is that the attacker uses harmful code and automated web approaches to distribute their malware. In this research,our contribution is twofold. Firstly, we examine a new attack vector that cyber adversaries can possibly use in the future to infect an operating system with a malware. Currently, attackers use various techniques to gain access to victims’ personal computers. Secondly, we present a novel automated web defence to countermeasure these malware attacks. The proposed research aims to provide a better understanding of the new computer virus-spreading techniques that intruders can use in the future. We provide the insight of these attacks and present ways to countermeasure the attacks and to reduce the attack surface. Experiments and flow diagrams have been used to demonstrate the attack and defence approach. To offer malware lateral movement and to encrypt the date of users’ device, we use Selenium automation tool on a social media platform. For our experimentation, we developed an application which has been tested on a variety of browsers including Google Chrome, Firefox, and Safari. Our research has revealed that we have an 85 percent success rate when testing in a head-on environment. We have expanded our experiments on headless applications and interestingly, the accuracy rate improved and the probability of success increased to 95 percent. Lastly, we have demonstrated a unique method for detecting and stopping web automation that is generally applicable.

The Wireless Sensor Network (WSN) has evolved into a new IoT scheme, and its adoption has no restrictions at present. Sadly, security has an impact on the network of wireless sensors, and Denial-of-Service (DOS) categories of attacks are security concerns. This study therefore focuses on the distributed denial of service (DDOS), especially on DDoS-PSH-ACK (ACK & PUSH ACK Flood) in WSN. An experimental analysis was developed to predict that many spoofed ACK packets were reoccurring in order to deflate the target node. In the proposed approach, several experimental scenarios for the DDOS detection function were established and implemented. The experimental analysis draws traffic flow within the several transmission sessions involving “the normal transmission within sensor nodes and cluster head”, as well as the “transmission and retransmission scenarios within the sensor nodes and cluster head” at same time with different signal sizes. The main contribution of the paper is predicting DDoS attack by variability of transmission behavior with high degree accuracy. It was established that the most ideal delay between transmissions is 23 milliseconds in order to ensure that the receiving end is not overwhelmed. The result of the current study highlighted that when transmission session gets overwhelmed, that influence DDOS success.

Crop monitoring and smart spraying have become indispensable parts of precision agriculture where unmanned aerial vehicles (UAVs) play a lead role. In particular, in large agricultural fields, aerial monitoring is a sustainable solution provided it can be performed in an energy-efficient manner. The existing literature points out that the research on precision agriculture using UAVs is still very minimal. In this article, we propose a support vector machine (SVM)-based UAV location management technique where UAVs change position over various portions or regions of a large agricultural field so that crops are properly monitored in an energy-efficient manner. Whenever a processing request is generated from any sensor in a part of the field, the UAV investigates with an SVM to decide whether to move on to the center of that field based on various parameters or characteristics such as region-id, packet-id, time of day, waiting times of the packets, the average waiting time of others within a predefined time window, location of the UAV, residual energy of the UAV after processing the packet, and movement after processing the packet. We use 70% of our data for training and the other 30% for testing. In our simulation study, we use accuracy, precision, and recall to measure in both contexts to determine the efficiency of the model, and also the amount of energy preserved is computed corresponding to every move. We also compare our approach with current state-of-the-art energy-preserving UAV movement control techniques which are compatible with the present application scenario. The proposed technique produced 6.5%, 34.5%, and 61.5% better results in terms of percentage of successful detection (PSD), composite energy consumption (CEC), and average delay (ADL), respectively.

Virtual Power Plants (VPPs) have emerged as dynamic solutions, harnessing the distributed resources such as solar panel and batteries. However, the complicated interconnectedness of VPPs exposes them to unique cybersecurity vulnerabilities, distinguishing them from traditional smart grids. This systematic literature review primarily focuses on the cybersecurity challenges VPPs face, such as data breaches and data flow manipulation. The study explores these unique risks based on proposed solutions from the existing literature like federated learning, intrusion detection systems, blockchain integration, and machine learning by analyzing their strengths, weaknesses, and applicability to VPP cybersecurity. Additionally, regulatory barriers and opportunities like cost-savings are discussed, with a focus on ensuring the secure future of VPPs through machine and deep learning and strong security policies. This paper contributes significantly to the field by identifying VPP cybersecurity risks, evaluating potential solutions, and proposing future research directions.