Towards Deep Learning-Based Approach for Detecting Android Malware

In this article, the authors implement a deep learning environment and fine-tune parameters to determine the optimal settings for the classification of Android malware from extracted permission data. By determining the optimal settings, the authors demonstrate the potential performance of a deep learning environment for Android malware detection. Specifically, an extensive study is conducted on various hyper-parameters to determine optimal configurations, and then a performance evaluation is carried out on those configurations to compare and maximize detection accuracy in our target networks. The results achieve a detection accuracy of approximately 95%, with an approximate F1 score of 93%. In addition, the evaluation is extended to include other machine learning frameworks, specifically comparing Microsoft Cognitive Toolkit (CNTK) and Theano with TensorFlow. The future needs are discussed in the realm of machine learning for mobile malware detection, including adversarial training, scalability, and the evaluation of additional data and features.

Effects of Team Collaboration on Sharing Information Security Advice

Active sharing of information security advice among the employees has undeniable implications for developing a sustainable security environment. This research examines this topic from the network perspective, and focuses on the work relationships that promote sharing security advice. Exponential random graph modeling technique was employed to evaluate the relationship between team collaborative activities and sharing security advice. The findings revealed that those who share security advice also tend to give work- and IT-related knowledge. Moreover, employees who have similar tenure tend to exchange security advice with each other more. Furthermore, the network of sharing security advice is transitive and has a tendency to form separate clusters. Security managers are suggested to take into account the research findings to identify key employees who frequently share security advice in the workplace and devise appropriate strategies to manage them.

Recent Development in Big Data Analytics

This chapter describes how big data consist of an extreme volume of data, velocity, and more complex variable data that demands current technology changes in capturing, storage, distribution, management, analysis data. Business facing more struggles in identifying the pragmatic approach in capturing the data about customer, products, and services. Usage of big data mainly with the analytical method, but it specifically compares with features of an analytical method based on unstructured data contributed around 95% of big data. The analytical approach depends on heterogeneous data and unstructured data's like text, audio, video format. It demands new effective tool for predictive analysis for big data with the unstructured format. This chapter describes explanation of big data and characteristics of big data compress of Volume, Velocity, Variety, Variability, and Value. Recent trends in the development of big data that applies in real time application perspectives like health care agriculture, education etc.

Overview of Machine Learning Approaches for Wireless Communication

Machine learning is one of the most popular research areas, and it is commonly used in wireless communications and networks. Security and fast communication are among of the key requirements for next generation wireless networks. Machine learning techniques are getting more important day-by-day since the types, amount, and structure of data is continuously changing. Recent developments in smart phones and other devices like drones, wearable devices, machines with sensors need reliable communication within internet of things (IoT) systems. For this purpose, artificial intelligence can increase the security and reliability and manage the data that is generated by the wireless systems. In this chapter, the authors investigate several machine learning techniques for wireless communications including deep learning, which represents a branch of artificial neural networks.

Machine Learning Techniques for Internet of Things

The idea of an intelligent, independent learning machine has fascinated humans for decades. The philosophy behind machine learning is to automate the creation of analytical models in order to enable algorithms to learn continuously with the help of available data. Since IoT will be among the major sources of new data, data science will make a great contribution to make IoT applications more intelligent. Machine learning can be applied in cases where the desired outcome is known (guided learning) or the data is not known beforehand (unguided learning) or the learning is the result of interaction between a model and the environment (reinforcement learning). This chapter answers the questions: How could machine learning algorithms be applied to IoT smart data? What is the taxonomy of machine learning algorithms that can be adopted in IoT? And what are IoT data characteristics in real-world which requires data analytics?

Scientific Intelligence, Decision Making, and Cyber-Security

Because of the huge amount of data and information in the decision-making and strategic choices processes, basing decisions on information directly collected from the sources is not conceivable. A decision-making analyst becomes a fundamental pillar in both the corporate field and the institutional world. This role is becoming increasingly complex and specialized, critical within the cycle of the intelligence analysis, for the relationships that bind it to the other stakeholders, and for the methodological and technological tools that support it. The purpose of this chapter is to explore the milestones of the intelligence analysis deriving from a close collaboration between social sciences, cognitive science, computer engineering, and ICT in order to respond to the different needs in the field of risk management, safety, investigations, and applied intelligence.

Research on Campus Network Security Problem and Protection Strategy

With the “Internet +” era of arrival, the major colleges and universities are in the construction of the wisdom of the campus, students and teachers living with the campus network is more and more closely related, Campus network security has become the protection of the wisdom of the campus construction. Campus network security issues become increasingly serious; a single security protection has been unable to meet the current security needs. This paper analyzes the major security threats facing the campus network, and presents the campus network security protection measures from the physical layer, network layer, system layer, application layer and management of five aspects, thus constructing the campus network's overall security defense system. The system has multiple security protection for Campus Network, thus improving the security of the campus network.

A Resourceful Approach in Security Testing to Protect Electronic Payment System Against Unforeseen Attack

This article describes how electronic payments are financial transactions made over the internet for goods or services. In the digital era, the e-commerce industry has gone beyond the traditional in-store service due to the wide spread of internet-based shopping. Developed countries are greatly relying on e-commerce business and a sizable number of countries have shown concern in regard to the online payment cards such as credit cards, debit cards, e-cash, e-cheques, e-wallets and smart card security. The main downsides are concerns over privacy or a malicious attack and hence safeguard mechanisms are required to protect personal information from falling into the hands of intruders. Before commercializing electronic payment systems (EPS), security tests play a significant role in the software development life cycle to check whether the system is secure and it is safe to use. A resourceful approach covering security policies, secure coding, security attack prevention methodology, security testing tool, security testing metrics, security test case prioritization techniques and a model for effective project management methodology are presented in this article. Early detection and resolution of security weaknesses can be achieved with the authors' proposed approach and would certainly reduce the time, effort and cost of a project. The proposed approach is likely the best-fit implementation of the payment industry, covering channels like B2C (Business to Consumer), C2C (Consumer to Consumer), C2B (Consumer to Business), B2B (Business to Business), People to People (P2P), G2C (Government to Citizen) and C2G (Citizen to Government).

Intelligent Malware Detection Using Deep Dilated Residual Networks for Cyber Security

Malware is the most serious security threat, which possibly targets billions of devices like personal computers, smartphones, etc. across the world. Malware classification and detection is a challenging task due to the targeted, zero-day, and stealthy nature of advanced and new malwares. The traditional signature detection methods like antivirus software were effective for detecting known malwares. At present, there are various solutions for detection of such unknown malwares employing feature-based machine learning algorithms. Machine learning techniques detect known malwares effectively but are not optimal and show a low accuracy rate for unknown malwares. This chapter explores a novel deep learning model called deep dilated residual network model for malware image classification. The proposed model showed a higher accuracy of 98.50% and 99.14% on Kaggle Malimg and BIG 2015 datasets, respectively. The new malwares can be handled in real-time with minimal human interaction using the proposed deep residual model.

The Usage Analysis of Machine Learning Methods for Intrusion Detection in Software-Defined Networks

This chapter focuses on the process of the machine learning with considering the architecture of software-defined networks (SDNs) and their security mechanisms. In general, machine learning has been studied widely in traditional network problems, but recently there have been a limited number of studies in the literature that connect SDN security and machine learning approaches. The main reason of this situation is that the structure of SDN has emerged newly and become different from the traditional networks. These structural variances are also summarized and compared in this chapter. After the main properties of the network architectures, several intrusion detection studies on SDN are introduced and analyzed according to their advantages and disadvantages. Upon this schedule, this chapter also aims to be the first organized guide that presents the referenced studies on the SDN security and artificial intelligence together.