Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Security experts have demonstrated numerous risks imposed by Internet of Things (IoT) devices on organizations. Due to the widespread adoption of such devices, their diversity, standardization obstacles, and inherent mobility, organizations require an intelligent mechanism capable of automatically detecting suspicious IoT devices connected to their networks. In particular, devices not included in a white list of trustworthy IoT device types (allowed to be used within the organizational premises) should be detected. In this research, Random Forest, a supervised machine learning algorithm, was applied to features extracted from network traffic data with the aim of accurately identifying IoT device types from the white list. To train and evaluate multi-class classifiers, we collected and manually labeled network traffic data from 17 distinct IoT devices, representing nine types of IoT devices. Based on the classification of 20 consecutive sessions and the use of majority rule, IoT device types that are not on the white list were correctly detected as unknown in 96% of test cases (on average), and white listed device types were correctly classified by their actual types in 99% of cases. Some IoT device types were identified quicker than others (e.g., sockets and thermostats were successfully detected within five TCP sessions of connecting to the network). Perfect detection of unauthorized IoT device types was achieved upon analyzing 110 consecutive sessions; perfect classification of white listed types required 346 consecutive sessions, 110 of which resulted in 99.49% accuracy. Further experiments demonstrated the successful applicability of classifiers trained in one location and tested on another. In addition, a discussion is provided regarding the resilience of our machine learning-based IoT white listing method to adversarial attacks.

Detection of Unauthorized IoT Devices Using Machine Learning Techniques

There is a wide range of interdisciplinary intersections between cyber security and artificial intelligence (AI). On one hand, AI technologies, such as deep learning, can be introduced into cyber security to construct smart models for implementing malware classification and intrusion detection and threating intelligence sensing. On the other hand, AI models will face various cyber threats, which will disturb their sample, learning, and decisions. Thus, AI models need specific cyber security defense and protection technologies to combat adversarial machine learning, preserve privacy in machine learning, secure federated learning, etc. Based on the above two aspects, we review the intersection of AI and cyber security. First, we summarize existing research efforts in terms of combating cyber attacks using AI, including adopting traditional machine learning methods and existing deep learning solutions. Then, we analyze the counterattacks from which AI itself may suffer, dissect their characteristics, and classify the corresponding defense methods. Finally, from the aspects of constructing encrypted neural network and realizing a secure federated deep learning, we expatiate the existing research on how to build a secure AI system.

Cyber security meets artificial intelligence: a survey

Background: With an explosive growth in mobile health, an estimated 500 million patients are potentially using mHealth apps for supporting health and self-care of chronic diseases. Therefore, this review focused on mHealth apps for use among patients with heart failure. Objective: The aim of this integrative review was to identify and assess the functionalities of mHealth apps that provided usability and efficacy data and apps that are commercially available without supporting data, all of which are to support heart failure self-care management and thus impact heart failure outcomes. Methods: A search of published, peer-reviewed literature was conducted for studies of technology-based interventions that used mHealth apps specific for heart failure. The initial database search yielded 8597 citations. After filters for English language and heart failure, the final 487 abstracts was reviewed. After removing duplicates, a total of 18 articles that tested usability and efficacy of mobile apps for heart failure self-management were included for review. Google Play and Apple App Store were searched with specified criteria to identify mHealth apps for heart failure. A total of 26 commercially available apps specific for heart failure were identified and rated using the validated Mobile Application Rating Scale. Results: The review included studies with low-quality design and sample sizes ranging from 7 to 165 with a total sample size of 847 participants from all 18 studies. Nine studies assessed usability of the newly developed mobile health system. Six of the studies included are randomized controlled trials, and 4 studies are pilot randomized controlled trials with sample sizes of fewer than 40. There were inconsistencies in the self-care components tested, increasing bias. Thus, risk of bias was assessed using the Cochrane Collaboration’s tool for risk of selection, performance, detection, attrition, and reporting biases. Most studies included in this review are underpowered and had high risk of bias across all categories. Three studies failed to provide enough information to allow for a complete assessment of bias, and thus had unknown or unclear risk of bias. This review on the commercially available apps demonstrated many incomplete apps, many apps with bugs, and several apps with low quality. Conclusions: The heterogeneity of study design, sample size, intervention components, and outcomes measured precluded the performance of a systematic review or meta-analysis, thus introducing bias of this review. Although the heart failure–related outcomes reported in this review vary, they demonstrated trends toward making an impact and offer a potentially cost-effective solution with 24/7 access to symptom monitoring as a point of care solution, promoting patient engagement in their own home care.

/pdf/mobile-phone-apps-to-support-heart-failure-self-care-4s7y6buhos.pdf

Mobile Phone Apps to Support Heart Failure Self-Care Management: Integrative Review.

In recent years, ransomware has been one of the most notorious malware targeting end users, governments, and business organizations. It has become a very profitable business for cybercriminals with revenues of millions of dollars, and a very serious threat to organizations with financial loss of billions of dollars. Numerous studies were proposed to address the ransomware threat, including surveys that cover certain aspects of ransomware research. However, no study exists in the literature that gives the complete picture on ransomware and ransomware defense research with respect to the diversity of targeted platforms. Since ransomware is already prevalent in PCs/workstations/desktops/laptops, is becoming more prevalent in mobile devices, and has already hit IoT/CPS recently, and will likely grow further in the IoT/CPS domain very soon, understanding ransomware and analyzing defense mechanisms with respect to target platforms is becoming more imperative. In order to fill this gap and motivate further research, in this paper, we present a comprehensive survey on ransomware and ransomware defense research with respect to PCs/workstations, mobile devices, and IoT/CPS platforms. Specifically, covering 137 studies over the period of 1990-2020, we give a detailed overview of ransomware evolution, comprehensively analyze the key building blocks of ransomware, present a taxonomy of notable ransomware families, and provide an extensive overview of ransomware defense research (i.e., analysis, detection, and recovery) with respect to platforms of PCs/workstations, mobile devices, and IoT/CPS. Moreover, we derive an extensive list of open issues for future ransomware research. We believe this survey will motivate further research by giving a complete picture on state-of-the-art ransomware research.

A Survey on Ransomware: Evolution, Taxonomy, and Defense Solutions.

Mobile computing has supplanted internet computing because of the proliferation of cloud-based applications and mobile devices (such as smartphones, palmtops, and tablets). As a result of this, wor...

https://journals.sagepub.com/doi/pdf/10.1177/2158244015580372

A Review of Bring Your Own Device on Security Issues

Ransomware is advanced and upgraded malicious software which comes in the forms of Crypto or Locker, with the intention to attack and take control of basic infrastructures and computer systems. The vast majority of these threats are aimed at directly or indirectly making money from the victims by asking for a ransom in exchange for decryption keys. This systematic literature analysed the anatomy of ransomware, including its trends and mode of attacks to find the possible solutions by querying various academic literature. In contrast to previous reviews, sources of ransomware dataset are revealed in this review paper to ease the challenges of researchers in getting access to ransomware datasets. In addition, a taxonomy of ransomware current trends is presented in the paper. We discussed the articles in detail, the evolution and trend in ransomware researches. Most of the techniques deployed could not completely prevent ransomware attacks because of its obfuscation techniques, but rather recommend proper and regular backup of important files. This review can serve as a benchmark for researchers in proposing a novel ransomware detection methodology and starting point for novice researchers.

Systematic literature review and metadata analysis of ransomware attacks and detection mechanisms

The growth of Internet of Things (IoT) took center stage universally due their capability to advance the course of human lives. Consequent upon this, several challenges were thrown up such as security of huge data stored and transmitted through network communication channels. IoT insecurity is partly due to centralization architecture, low computational strength, resource-constrained devices, variation in standards and protocols of communication. From this Systematic Literature Review (SLR), the 85 articles reviewed showed that privacy and security solutions are still being proposed or at conceptual levels, though a number of researchers favored the integration of Blockchain technology, cryptographic and hashing schemes into IoT. The Blockchain technology in IoT systems remains an open area of interest for top researchers especially in evolving frameworks to fit into the centralized architecture, functionality, and scalability demands of conventional IoT systems. In this article, we investigate security and privacy concerns of IoT from the lens of current trends, pertinent challenges, security methodologies, applications, and gaps for future research directions. Most specifically, there is prospect of utilizing cryptographic and hashing schemes offered by Blockchain technology in IoT. Then, high performance and scalable cryptographic schemes (that is, those in the class of lightweight appraoch) are suggested to deal with privacy and security of data in Blockchain-based IoT system. More importantly, this study provides basis for evolving secure and decentralized applications and systems in several domains such as smart farming.

Blockchain technology in IoT systems: current trends, methodology, problems, applications, and future directions

This study identifies and evaluates discriminative lexical features of malware URLs for building a real-time malware URL classification. The lexical features of malware URL are first identified from existing blacklisted malware URLs through manual examination. Feature identification is followed by studying the prevalence of these features on newly collected malware URLs through empirical analysis. Our empirical analysis revealed that attackers follow the same pattern in crafting malware URL. To evaluate the performance and effectiveness of these features, we applied a Support Vector Machine (SVM) classification algorithm on a dataset comprising of benign and malware URLs. By applying the WEKA data mining tool on our trained dataset, a 96.95 % accuracy was achieved with a low False Negative Rate (FNR) of 0.018 and a moderate False Positive Rate (FPR) of 0.046.

Identification and Evaluation of Discriminative Lexical Features of Malware URL for Real-Time Classification

Botnet is one of the major security threats in the field of information technology today (IT). The increase in the rate of attack on industrial IT infrastructures, theft of personal data and attacks on financial information is becoming critical. Majority of available dataset for botnet detection are very old and may not be able to stand the present reality in this research area. One of the latest dataset from Canadian Institute of Cyber Security labeled “CICIDS2017” was noted as an imbalance data distribution ratio of 99% to 1%. This distribution represents majority to minority class ratio. This may pose a challenge of over-fitting in majority class to the research and create a bias in the analysis of results. This research work has adopted J48 decision tree machine learning algorithm with application of SMOTE technique in solving the problem of imbalance dataset, thereby leading to an improved detection of botnets. The accuracy of the highest scenario was 99.95%. This is a significant improvement in detection rate compare to the previous research work.

Morufu Olalere

Papers

A Review of Bring Your Own Device on Security Issues

Systematic literature review and metadata analysis of ransomware attacks and detection mechanisms

Blockchain technology in IoT systems: current trends, methodology, problems, applications, and future directions

Identification and Evaluation of Discriminative Lexical Features of Malware URL for Real-Time Classification

Enhanced Decision Tree-J48 With SMOTE Machine Learning Algorithm for Effective Botnet Detection in Imbalance Dataset