Lately, Deep learning and machine learning models have been vividly used in image classification to measure the accuracy of the proposed model. Deep learning networks always require high computing networks to increase the model's performance. Computer vision plays a vital role in polishing the dataset by removing unwanted information, without the loss of important features. As per certain applications, two machine learning and deep learning algorithms with different system requirements are compared and summarized. In this paper, instead of the RGB image dataset, the thermogram image dataset has been considered for the process. The main concern in considering thermal images is due to the particular application. Here the thermal images have been collected during the nocturnal hours, especially on the dawn and dusk of the day. Convolutional neural networks are the machine learning models used in CPU and GPU-cluster configurations. AlexNet will be the deep learning model used here to compare with the CNN supervised learning algorithm. Computer vision technique, HOG is used to reduce the complexity and intricacy of the dataset before getting into the network models. Because of the usage of deep network models' performance computing is expended to increase the speed of the whole process. Deer will be the spotted animal for most road accidents during the nocturnal hours in the United States. The results gaudily conclude the classification of machine learning and deep learning model detection for thermal and HOG images with the highest accuracy of 92% for the AlexNet.

The growing use of media has led to the development of several machine learning (ML) and natural language processing (NLP) tools to process the unprecedented amount of social media content to make actionable decisions. However, these ML and NLP algorithms have been widely shown to be vulnerable to adversarial attacks. These vulnerabilities allow adversaries to launch a diversified set of adversarial attacks on these algorithms in different applications of social media text processing. In this article, we provide a comprehensive review of the main approaches for adversarial attacks and defenses in the context of social media applications with a particular focus on key challenges and future research directions. In detail, we cover literature on six key applications: 1) rumors detection; 2) satires detection; 3) clickbaits and spams identification; 4) hate speech detection; 5) misinformation detection; and 6) sentiment analysis. We then highlight the concurrent and anticipated future research questions and provide recommendations and directions for future work.

The coronavirus (COVID-19) started in China in 2019, has spread rapidly in every single country and has spread in millions of cases worldwide. This paper presents a proposed approach that involves identifying the relative impact of COVID-19 on a specific gender, the mortality rate in specific age, investigating different safety measures adopted by each country and their impact on the virus growth rate. Our study proposes data-driven analysis and prediction modeling by investigating three aspects of the pandemic (gender of patients, global growth rate, and social distancing). Several machine learning and ensemble models have been used and compared to obtain the best accuracy. Experiments have been demonstrated on three large public datasets. The motivation of this study is to propose an analytical machine learning based model to explore three significant aspects of COVID-19 pandemic as gender, global growth rate, and social distancing. The proposed analytical model includes classic classifiers, distinctive ensemble methods such as bagging, feature based ensemble, voting and stacking. The results show a superior prediction performance comparing with the related approaches.

Phishing attacks have witnessed a rapid increase thanks to the matured social engineering techniques, COVID-19 pandemic, and recently adversarial deep learning techniques. Even though adversarial phishing attacks are recent, attackers are crafting such attacks by considering context, testing different attack paths, then selecting paths that can evade machine learning phishing detectors. This research proposes an approach that generates adversarial phishing attacks by finding optimal subsets of features that lead to higher evasion rate. We used feature engineering techniques such as Recursive Feature Elimination, Lasso, and Cancel Out to generate then test attack vectors that have higher potential to evade phishing detectors. We tested the evasion performance of each technique then classified different evasion tests as passed or failed depending on their evasion rate. Our findings showed that our threat model has better evasion capability compared to the original Generative Adversarial Deep Neural Network (GAN) which perturbs features in a random manner.

In this paper we proposed a model to investigate the behaviour of websites when dealing with invalid inputs. Many vulnerabilities rise from invalid inputs. An invalid input is considered as a form of a successful attack if it is processed by the website code or back-end database. Based on this assumption, we proposed a list of indicators that tested and processed invalid inputs. A tool is developed to implement this model. We tested the model through evaluating several websites selected randomly. Our tool has no special credentials or access to any of the tested websites. We found many SQL injection vulnerabilities based on our proposed model. Upon the manual investigation of the web pages that showed such vulnerabilities, we found few instances of false positives. We believe that this can provide a systematic and automated approach to test websites for vulnerabilities related to improper input validation.

The number of new cases of infection of the Coronavirus disease, COVID-19, is alarming in many places in the world. In several world countries, including USA, the infection rates and daily cases numbers are fairly high; and there are even some spike increases in some USA states. Since the USA is experiencing the highest number of daily new cases in the world from May through July, the most important question is when we will witness an effective decline in the number of daily new cases? This paper follows a data-driven approach to induce the disease decline values from two country groups in the world where the disease declined already to less than 25% of its peak daily new cases. We apply these country groups' models to predict the decline to 25% of the US's peak. We compiled, examined, and analyzed pandemic data and statistics of two countries: g1: 42 countries, and g2: 14 countries. We utilize their data in the prediction of the decline timeline of the US. Group g2 consists of 14 countries having a similar number of cases per one million population. The majority of the models predict that the decline to 25% of the US's peak will be around the end of November to the first week of October. The results are significant and impressive as it is highly demanded to have clues and methods for the timeline prediction of this pandemic in the USA.

This paper examines multiple machine learning models to find the model that best indicates anomalous activity in an industrial control system that is under a software-based attack. The researched machine learning models are Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Recurrent Neural Network classifiers built-in Python and tested against the HIL-based Augmented ICS dataset. Although the results showed that Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Long Short-Term Memory classification models have great potential for anomaly detection in industrial control systems, we found that Random Forest with tuned hyperparameters slightly outperformed the other models.

The spread of violent extremism and propaganda is a critical threat both nationally and globally. With the ever-increasing popularity and use of social media, spreading this extremism has never been easier for terrorist organizations and their followers. One terrorist organization, in particular, ISIS (the Islamic State of Iraq and Syria), uses Twitter for the vast majority of their social media interaction. It is crucial to have cyber analytics tools developed to combat these extremists' online presence and influence on social media platforms, such as Twitter. In this research, we apply machine learning algorithms to understand popular ISIS supporters' behavior and techniques and their possible influence on other users. We collected and analyzed a dataset containing over seventeen thousand tweets posted by pro-ISIS Twitterers. We utilized three machine learning algorithms with several models/settings in an attempt to classify and predict whether the top 4 pro-ISIS Twitter users (the most followed and tweeted users) authored a specific tweet. The algorithms applied in this work include sequential neural networks, random forests, and XGBoost. The models were ensembled, timed, and one model was simplified to attempt to improve performance and runtime.

Computing networks integrate systems, services, and users around the world. Hundreds of protocols contribute to making such process flawless. A fault in protocol design or implementation can impact many users and interrupt their tasks’ workflows. Testing network protocols, whether static or dynamic, can take several approaches. Driven by the expansion of applications in different domains, in this paper, we evaluated fault-based testing techniques in testing network protocols. Out fault-based testing requirements are extracted based on network protocols’ specifications. Our main goal is to test whether fault-based testing techniques can find faults or bugs that cannot be discovered by classical network protocols’ testing techniques. One of the significant functional testing areas that fault-based techniques can work well in is conformance testing. They can test whether the network protocol is robust enough to validate test cases that conform with protocol specification and, on the other hand, invalidate test cases that do not show such conformance. We showed through several experiments that fault-based testing can prove conformance with less effort required through other testing approaches. Generated test scenarios serve as input for the network simulator. The quality of the test scenarios is evaluated based on three perspectives: (i) code coverage, (ii) mutation score, and (iii) testing effort. We implemented the testing framework in NS2. Experiments can be recreated using other simulation environments.

Companies' web portals are key gateways to those companies for products' search, customer services, etc. The volume of search for a particular company, and its website through the Internet and search engines can be a metric on its web popularity. Our goal in this paper is to study, the relation, if any, between the change in volume of users' searching for companies through the Internet and companies' stock price changes. We expect to see different types of levels of impacts/correlations between those two factors for different reasons. For example stock prices can change for many different reasons where some of those reasons may have nothing to do with customers at all. Second is that same factors can have different impact on the different companies. For example, while in some IT or technology related companies ' web popularity can be a significant factor or indicator, in many other companies, such popularity is not significant at all. In this paper, we studied historical stock prices for a selected dataset of companies(S&P 500) along with the search or interest in those companies (based on Google search queries). We created and evaluated a dataset of search terms and their correlations with stock price change of S&P 500 companies. Results showed that different companies can be influenced by popular search terms at different weights. We distinguished also in our work between negative or positive influence where keywords can be correlated to the decrease or increase of stock prices.

Since its introduction several years ago, Shodan has been used in several research projects related to security assessment of IoT devices publicly facing the Internet. Despite the fact that many of the queries that can expose those devices are publicly known, yet subsequent assessments continue to indicate the existence of instances of those vulnerabilities. In this paper, we conducted a remote security assessment based on an extended dataset from original public Shodan queries (with known terms to expose vulnerabilities). Based on our own assessment for the terms in the public Shodan queries, we updated the list to cover other important query terms that were reported for remote back-door access. Results showed that many of those public queries in the original Shodan list can still exploit several systems and devices facing the Internet. Similarly, many of the newly added queries indicate existing vulnerabilities in some live systems in the US in particular and also worldwide. Vulnerabilities related to default or trivial passwords in IoT devices were reported in SHINE and other assessment projects. Nonetheless, many of those vulnerabilities that are easy to fix, still exist in publicly visible IoT devices.

Summary Target‐Decoy database is currently the method of choice to assess the quality of Proteins' search engines. Decoy versions of real peptides are generated and injected to the same database of real ones with different labels. Quality of search engines results is assessed based on the number of decoys retrieved as hits. In Crux‐Tide search engine, which is one of the fastest search engines currently available, the process of indexing and generating decoys is computationally expensive. In this paper, we analyze the serial algorithm in detail and show improvement possibilities, and then describe a parallel‐shared memory solution using OpenMP. To completely break up the dependency in the serial algorithms, a clever hashing technique is utilized to localize the process. The parallel solution and the hashing technique together are able to reduce the computation cost by approximately 70‐80% using few threads. Besides the parallelization, we redesign part of the serial code so that the memory consumption becomes more efficient. The parallel version can index the same files using around two‐third of the memory space that the serial version consumes. This solution could impact and support future distributed developments of Crux‐Tide searching phase, where each parallel unit could rank the observed spectra independently.

several peptides search engines have been developed in the recent decades. Most of the time and for the same inputs, different search engines’ result in different peptides were identified, which can confuse the stakeholders in the field of proteomics. The massive amount of generated spectra by high throughput spectrometers adds another challenge which handicaps the current search engines. This motivates the researchers to evaluate the combination of several search engines. Several studies provided ensemble solutions over shared and distributed computing environments for reliable results. However, the massive amount of MS/MS spectra is a cumbersome traffic over the systems’ networks. This issue directly impacts the searching performance and also adds unnecessary extra costs (computing, storage, network traffic) if cloud cluster is being used. The main question of this paper is: Can we build a central MS/MS spectra preprocessing for semantically different protein search engines? We evaluate different statistical reduction techniques using four popular protein search engines. In order to fairly evaluate the results, we build ground truth unanimous-based datasets for two different species; yeast and human. Our techniques result in significant peak reduction, where only around 30% of the spectra peaks are enough to report reliable identifications from the used search engines in this study.

The diversity of the available protein search engines with respect to the utilized matching algorithms, the low overlap ratios among their results and the disparity of their coverage encourage the community of proteomics to utilize ensemble solutions of different search engines. The advancing in cloud computing technology and the availability of distributed processing clusters can also provide support to this task. However, data transferring and results' combining, in this case, could be the major bottleneck. The flood of billions of observed mass spectra, hundreds of Gigabytes or potentially Terabytes of data, could easily cause the congestions, increase the risk of failure, poor performance, add more computations' cost, and waste available resources. Therefore, in this study, we propose a deep learning model in order to mitigate the traffic over cloud network and, thus reduce the cost of cloud computing. The model, which depends on the top 50 intensities and their m/z values of each spectrum, removes any spectrum which is predicted not to pass the majority voting of the participated search engines. Our results using three search engines namely: pFind, Comet and X!Tandem, and four different datasets are promising and promote the investment in deep learning to solve such type of Big data problems.

Despite the linear relation between the number of observed spectra and the searching time, the current protein search engines, even the parallel versions, could take several hours to search a large amount of MSMS spectra, which can be generated in a short time. After a laborious searching process, some (and at times, majority) of the observed spectra are labeled as non-identifiable. We evaluate the role of machine learning in building an efficient MSMS filter to remove non-identifiable spectra. We compare and evaluate the deep learning algorithm using 9 shallow learning algorithms with different configurations. Using 10 different datasets generated from two different search engines, different instruments, different sizes and from different species, we experimentally show that deep learning models are powerful in filtering MSMS spectra. We also show that our simple features list is significant where other shallow learning algorithms showed encouraging results in filtering the MSMS spectra. Our deep learning model can exclude around 50% of the non-identifiable spectra while losing, on average, only 9% of the identifiable ones. As for shallow learning, algorithms of: Random Forest, Support Vector Machine and Neural Networks showed encouraging results, eliminating, on average, 70% of the non-identifiable spectra while losing around 25% of the identifiable ones. The deep learning algorithm may be especially more useful in instances where the protein(s) of interest are in lower cellular or tissue concentration, while the other algorithms may be more useful for concentrated or more highly expressed proteins.

Sentiment Analysis (SA) is one of the hottest research fields nowadays. It is concerned with identifying the sentiment conveyed in a piece of text. The current efforts in SA require the existence of standard datasets for training/testing purposes. Such datasets already exist for some languages such as English. Unfortunately, the same cannot be said about other languages such as Arabic. Currently existing Arabic SA datasets are restricted (in their domain, size, dialects covered, etc.) and/or have limited availability. Moreover, the annotation process did not receive the proper attention it deserves. Some of the existing datasets relied on the author's point of view for annotation, while others employed annotators, but did not take into account the personal variations between the annotators and how would that affect their agreement. This study presents our efforts to build a standard Arabic dataset with the above concerns in mind. The constructed dataset is intended for generic use as it contains reviews from different domains written in Modern Standard Arabic (MSA) as well as several dialects. As for the annotation process, it is given high attention by studying the inter-annotator agreements and investigating the potential factors affecting them.

In online social networks (OSNs), individual users have a strong desire to expand their social networks through OSN activities and try to maximize the benefits from the social relationships, called social capital. However, with a large-scale social network, their privacy rights have been significantly intruded by adversarial users that perform social attacks including false / illegal private information dissemination or the use of fake identities. In this work, we study how individual users can expand their social networks by making trustworthy friends while not leaking their private information out to unauthorized parties or social attackers. We adopt the concepts of trust and reputation in order to preserve users' privacy while enhancing their social capital in OSNs. Given a social network topology from the Facebook, we model an individual user's interactions with other users based on feeding (e.g., posting information) and feedback behaviors (e.g., providing likes or comments). Our results show that there exists a tradeoff between social capital and privacy preservation. In addition, we show there exists a balance point of social capital and privacy thresholds that maximizes correct information diffusion while minimizing illegal private information leakout, given users' risk appetite for preserving privacy.

Due to the proliferation of using various online social media, individual users put their privacy at risk by posting and exchanging enormous amounts of messages or activities with other users. This causes a serious concern about leaking private information out to malevolent entities without users’ consent. This work proposes a reputation model in order to achieve efficient and effective privacy preservation in which a user’s reputation score can be used to set the level of privacy and accordingly to determine the level of visibility for all messages or activities posted by the users. We derive a user’s reputation based on both individual and relational characteristics in online social network environments. We demonstrate how the proposed reputation model can be used for automatic privacy assessment and accordingly visibility setting for messages / activities created by a user.

The recent emerge of Software Defined Networking (SDN) promotes both supporters and opponents to further explore this network architecture. One of the main attributes that characterize SDN is the significant role of software to manage and control the architecture. There are four major concerns for such software dominant role, security, performance, reliability, and fault tolerance. Among them security is considered a major concern. SDNs security concerns include attacks on the control plane layer such as DoS attacks. This paper presents an inference-relation context based technique for the detection of DoS attacks on SDNs. The proposed technique utilizes contextual similarity with existing attack patterns to identify DoS in an OpenFlow infrastructure. A validation of the proposed technique has been performed using a several benchmark datasets yielding promising results.

The analysis of large-scale data for the purpose of extracting patterns is applicable to several research fields. In this paper, a dataset of climate related historical data from Jordan is collected. The main focus is to study evolution criteria of weather attributes in Jordan over the evaluated period of time and how it is connected to climate change. Results showed that humidity and dew point weather attributes are going to face a significant increase in the future. Such an increase is expected to have a direct, as well as an indirect impact on human life.

Aspects can be used in a harmful way that invalidates desired properties. Rigorous specification and analysis of aspect design is thus highly desirable. This paper presents an approach to model-checking state-based specification of aspect-oriented design. It is based on a rigorous formalism for capturing crosscutting concerns with respect to the design-level state models of classes. An aspect model not only encapsulates pointcuts and advice, but also supports inter-model declarations, aspect precedence, and references to the behaviors of other classes in advice models. For verification purposes, we convert the aspect-oriented state model of a system into woven models and further transform the woven models and the non-base class models into FSP processes. The generated FSP processes are checked by the LTSA model checker against the desired system properties. We have applied our approach to the modeling and verification of a non-trivial aspect-oriented cruise control system. A total of 21 properties that provide a comprehensive coverage of the system requirements are successfully formalized and verified.

Source code analysis is important for software management. It enables us to recognize strengths and weaknesses in our earlier projects or releases. We developed a source code analysis tool. This tool gathers several metrics from C/C++, C# or Java source codes. In this paper, we use the tool to analyze some of the open source code projects. We study the selected projects release evolutions and compare some characteristics between the same project releases, as well as among different projects. Different programming language code and development styles are studied through those open source projects