Melbourne Polytechnic

Machine learning techniques are being widely used to develop an intrusion detection system (IDS) for detecting and classifying cyberattacks at the network-level and the host-level in a timely and automatic manner. However, many challenges arise since malicious attacks are continually changing and are occurring in very large volumes requiring a scalable solution. There are different malware datasets available publicly for further research by cyber security community. However, no existing study has shown the detailed analysis of the performance of various machine learning algorithms on various publicly available datasets. Due to the dynamic nature of malware with continuously changing attacking methods, the malware datasets available publicly are to be updated systematically and benchmarked. In this paper, a deep neural network (DNN), a type of deep learning model, is explored to develop a flexible and effective IDS to detect and classify unforeseen and unpredictable cyberattacks. The continuous change in network behavior and rapid evolution of attacks makes it necessary to evaluate various datasets which are generated over the years through static and dynamic approaches. This type of study facilitates to identify the best algorithm which can effectively work in detecting future cyberattacks. A comprehensive evaluation of experiments of DNNs and other classical machine learning classifiers are shown on various publicly available benchmark malware datasets. The optimal network parameters and network topologies for DNNs are chosen through the following hyperparameter selection methods with KDDCup 99 dataset. All the experiments of DNNs are run till 1,000 epochs with the learning rate varying in the range [0.01-0.5]. The DNN model which performed well on KDDCup 99 is applied on other datasets, such as NSL-KDD, UNSW-NB15, Kyoto, WSN-DS, and CICIDS 2017, to conduct the benchmark. Our DNN model learns the abstract and high-dimensional feature representation of the IDS data by passing them into many hidden layers. Through a rigorous experimental testing, it is confirmed that DNNs perform well in comparison with the classical machine learning classifiers. Finally, we propose a highly scalable and hybrid DNNs framework called scale-hybrid-IDS-AlertNet which can be used in real-time to effectively monitor the network traffic and host-level events to proactively alert possible cyberattacks.

Security breaches due to attacks by malicious software (malware) continue to escalate posing a major security concern in this digital age. With many computer users, corporations, and governments affected due to an exponential growth in malware attacks, malware detection continues to be a hot research topic. Current malware detection solutions that adopt the static and dynamic analysis of malware signatures and behavior patterns are time consuming and have proven to be ineffective in identifying unknown malwares in real-time. Recent malwares use polymorphic, metamorphic, and other evasive techniques to change the malware behaviors quickly and to generate a large number of new malwares. Such new malwares are predominantly variants of existing malwares, and machine learning algorithms (MLAs) are being employed recently to conduct an effective malware analysis. However, such approaches are time consuming as they require extensive feature engineering, feature learning, and feature representation. By using the advanced MLAs such as deep learning, the feature engineering phase can be completely avoided. Recently reported research studies in this direction show the performance of their algorithms with a biased training data, which limits their practical use in real-time situations. There is a compelling need to mitigate bias and evaluate these methods independently in order to arrive at a new enhanced method for effective zero-day malware detection. To fill the gap in the literature, this paper, first, evaluates the classical MLAs and deep learning architectures for malware detection, classification, and categorization using different public and private datasets. Second, we remove all the dataset bias removed in the experimental analysis by having different splits of the public and private datasets to train and test the model in a disjoint way using different timescales. Third, our major contribution is in proposing a novel image processing technique with optimal parameters for MLAs and deep learning architectures to arrive at an effective zero-day malware detection model. A comprehensive comparative study of our model demonstrates that our proposed deep learning architectures outperform classical MLAs. Our novelty in combining visualization and deep learning architectures for static, dynamic, and image processing-based hybrid approach applied in a big data environment is the first of its kind toward achieving robust intelligent zero-day malware detection. Overall, this paper paves way for an effective visual detection of malware using a scalable and hybrid deep learning framework for real-time deployments.

Nowadays, the Industrial Internet of Things (IIoT) has remarkably transformed our personal lifestyles and society operations into a novel digital mode, which brings tremendous associations with all walks of life, such as intelligent logistics, smart grid, and smart city. Moreover, with the rapid increase of IIoT devices, a large amount of data is swapped between heterogeneous sensors and devices every moment. This trend increases the risk of eavesdropping and hijacking attacks in communication channels, so maintaining data privacy and security becomes two notable concerns at present. Recently, based on the mechanism of the Schnorr signature, a more secure and lightweight certificateless signature (CLS) protocol is popular for the resource-constrained IIoT protocol design. Nevertheless, we found most of the existing CLS schemes are susceptible to several common security weaknesses such as man-in-the-middle attacks, key generation center compromised attacks, and distributed denial of service attacks. To tackle the challenges mentioned previously, in this article, we propose a novel pairing-free certificateless scheme that utilizes the state-of-the-art blockchain technique and smart contract to construct a novel reliable and efficient CLS scheme. Then, we simulate the Type-I and Type-II adversaries to verify the trustworthiness of our scheme. Security analysis as well as performance evaluation outcomes prove that our design can hold more reliable security assurance with less computation cost (i.e., reduced by around 40.0% at most) and communication cost (i.e., reduced by around 94.7% at most) than other related schemes.

Fossil fuel energy resources are depleting rapidly and most importantly the liquid fossil fuel will be diminished by the middle of this century. In addition, the fossil fuel is directly related to air pollution, land and water degradation. In these circumstances, biofuel from renewable sources can be an alternative to reduce our dependency on fossil fuel and assist to maintain the healthy global environment and economic sustainability. Production of biofuel from food stock generally consumed by humans or animals can be problematic and the root cause of worldwide dissatisfaction. Biofuels production from microalgae can provide some distinctive advantages such as their rapid growth rate, greenhouse gas fixation ability and high production capacity of lipids. This paper reviews the current status of biofuel from algae as a renewable source.

With the explosion of Internet of Things (IoT) worldwide, there is an increasing threat from malicious software (malware) attackers that calls for efficient monitoring of vulnerable systems. Large amounts of data collected from computer networks, servers, and mobile devices need to be analysed for malware proliferation. Effective analysis methods are needed to match with the scale and complexity of such a data-intensive environment. In today’s Big Data contexts, visualisation techniques can support malware analysts going through the time-consuming process of analysing suspicious activities thoroughly. This paper takes a step further in contributing to the evolving realm of visualisation techniques used in the information security field. The aim of the paper is twofold: <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mo stretchy="false">(</mml:mo><mml:mn fontstyle="italic">1</mml:mn><mml:mo stretchy="false">)</mml:mo></mml:math> to provide a comprehensive overview of the existing visualisation techniques for detecting suspicious behaviour of systems and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mo stretchy="false">(</mml:mo><mml:mn fontstyle="italic">2</mml:mn><mml:mo stretchy="false">)</mml:mo></mml:math> to design a novel visualisation using similarity matrix method for establishing malware classification accurately. The prime motivation of our proposal is to identify obfuscated malware using visualisation of the extended x86 IA-32 (opcode) similarity patterns, which are hard to detect with the existing approaches. Our approach uses hybrid models wherein static and dynamic malware analysis techniques are combined effectively along with visualisation of similarity matrices in order to detect and classify zero-day malware efficiently. Overall, the high accuracy of classification achieved with our proposed method can be visually observed since different malware families exhibit significantly dissimilar behaviour patterns.

BACKGROUND: Clinical activities that trainees can be trusted to perform with minimal or no supervision have been labelled as Entrustable Professional Activities (EPAs). We sought to examine what activities could be entrusted to psychiatry trainees in their first year of specialist training. METHODS: We conducted an online survey of Fellows of the Royal Australian and New Zealand College of Psychiatrists (RANZCP). RESULTS: The majority of respondents considered initiating patients with the common medications, discharging patient suffering from schizophrenia, bipolar disorder or following a crisis admission, conducting risk assessments and managing psychiatric emergencies were activities that trainees could be entrusted with by the end of the first stage of training. CONCLUSIONS: Four activities were identified that trainees should be entrusted with by the end of their first year of training. Each of these activities comprises a set of competencies in each of the CanMEDS roles. When a trainee is unable to satisfactorily perform an EPA, deficits in the underpinning competencies can be a focus for remediation. Further EPAs are being identified in areas of more specialised practice for use within more advanced training.

The complexity, sophistication, and impact of malware evolve with industrial revolution and technology advancements. This article discusses and proposes a robust cross-architecture IoT malware threat hunting model based on advanced ensemble learning (MTHAEL). Our unique MTHAEL model using stacked ensemble of heterogeneous feature selection algorithms and state-of-the-art neural networks to learn different levels of semantic features demonstrates enhanced IoT malware detection than existing approaches. MTHAEL is the first of its kind that effectively optimizes recurrent neural network (RNN) and convolutional neural network (CNN) with high classification accuracy and consistently low computational overheads on different IoT architectures. Cross-architecture benchmarking is performed during the training with different architectures such as ARM, Intel80386, MIPS, and MIPS+Intel80386 individually. Two different hardware architectures were employed to analyze the architecture overhead, namely Raspberry Pi 4 (ARM-based architecture) and Core-i5 (Intel-based architecture). Our proposed MTHAEL is evaluated comprehensively with a large IoT cross-architecture dataset of 21,137 samples and has achieved 99.98 percent classification accuracy for ARM architecture samples, surpassing prior related works. Overall, MTHAEL has demonstrated practical suitability for cross-architecture IoT malware detection with low computational overheads requiring only 0.32 seconds to detect Any IoT malware.

The rapid development of Internet of Things (IoT) stimulates the innovation for the health-related devices such as remote patient monitoring, connected inhalers and ingestible sensors. Simultaneously, with the aid of numerous equipments, a great number of collected data can be used for disease prediction or diagnosis model establishment. However, the potential patient data leak will also bring privacy and security issues in the interaction period. To deal with these existing issues, we propose a decentralized, efficient, and privacy-enhanced federated edge learning system called DEEP-FEL, which enables medical devices in different institutions to collaboratively train a global model without raw data mutual exchange. Firstly, we design a hierarchical ring topology to alleviate centralization of the conventional training framework, and formulate the ring construction as an optimization problem, which can be solved by an efficient heuristic algorithm. Subsequently, we design an efficient parameter aggregation algorithm for distributed medical institutions to generate a new global model, and the total amount of data transmitted by N nodes is only <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2/N$</tex-math></inline-formula> times that of traditional algorithm. In addition, data security among different medical institutions is enhanced by adding artificial noise to the edge model. Finally, experimental results on three medical datasets demonstrate the superiority of our system.

Creative and performing arts schools are increasingly facing the challenge of developing curricula to address an employability agenda in higher education. Arts entrepreneurship education is thought to address this need because it supports the unique nature of the work circumstances of creative and performing arts graduates. As an emerging area of research, arts entrepreneurship education faces the challenge of not only being relevant and important to creative and performing arts education but of being robust enough to contribute to a "paradigm shift" (Beckman, 2011, p. 29). With this in mind, this article attempts to clarify a recurring theme of arts entrepreneurship education, this being the development of an "entrepreneurial mindset." We argue that if an entrepreneurial mindset is to be considered an essential aspect of arts entrepreneurship education, educators need to have a good understanding of what it means and how it might be taught. We examine data from four interviews with arts educators who have responsibility for teaching arts entrepreneurship in creative and performing arts schools. Their experiences enable us to clarify the meaning of an "entrepreneurial mindset" in a creative and performing arts context in higher education and to make suggestions about teaching and learning.

Today, great potential is envisaged for ERP systems in small and medium-sized enterprises (SMEs), and software vendors have been repackaging their ERP systems for SMEs with a recent focus on cloud-based systems. While cloud ERP offers the best solution for SMEs without the overheads of the huge investment and management costs that are associated with traditional ERP systems, the SME sector faces many challenges in their adoption. Traditional ERP studies have predominantly focused on large organizations, and gaps in the literature indicate that both vendor and consumer perspectives require more understanding with new technology offerings for SMEs. This paper describes some of the common challenges, such as cost effectiveness, alignment between software and business processes, customized governance and training, which form the major SME constraints for ERP system adoption. Due to the dynamic nature of SME businesses, best practice guidelines for an SME’s ERP implementation could be arrived at through closer investigation of its business requirements in order to avoid misfits. This forms the main objective of the study. We identify key success factors of ERP implementation in an Australian SME as a case study. These target success factors are then compared to the actual outcomes achieved. Factors such as business process alignment with the ERP system, meeting customer and stakeholder needs and reducing recurring and maintenance costs were key to the success of ERP implementation for the Australian SME. In particular, the IT and business strategy alignment with a customer focus and flexible reporting features of ERP systems has resulted in business agility.

Energy-efficient Cloud Infrastructure Resource Allocation Framework is getting popularity as it is paying effective attention to cloud data management with a view to achieve maximize revenue and minimize cost. This infrastructure can encourage for both cloud providers and users for allocating cloud infrastructure resources for fulfilling not only good energy efficiency measured in Power Usage Effectiveness (PUE) and data center Infrastructure Efficiency (DCiE) but also high CPU utilization. Therefore, in this paper we proposed a framework which can show effective performance for achieving the high data center energy efficiency and preventing Service Level Agreement (SLA) violation respectively with the aim of green cloud resources deployment. The framework accomplishes cloud infrastructure resource allocation on the basic of Reinforcement Learning mechanism and Fuzzy Logic for green solutions. The evaluation for Energy-efficient Resource Allocation is experimented on the traces of the PlanetLab virtualized environment for gaining good PUE and CPU utilization.

Anther development progresses through 15 distinct developmental stages in wheat, and accurate determination of anther developmental stages is essential in anther and pollen studies. A detailed outline of the development of the wheat anther through its entire developmental program, including the 15 distinct morphological stages, is presented. In bread wheat (Triticum aestivum), anther developmental stages were correlated with five measurements, namely auricle distance, spike length, spikelet length, anther length and anther width. Spike length and auricle distance were shown to be suitable for rapid anther staging within cultivars. Anther length is an accurate measurement in determining anther stages and may be applicable for use between cultivars. Tapetal Programmed Cell Death (PCD) in wheat begins between late tetrad stage (stage 8) and the early young microspore stage (stage 9) of anther development. Tapetal PCD continues until the vacuolate pollen stage (stage 11), at which point the tapetum fully degrades. The timing of tapetal PCD initiation is slightly delayed compared to that in rice, but is two stages earlier than in the model dicot Arabidopsis. The MYB80 gene, which encodes a transcription factor regulating the timing of tapetal PCD, reaches its peak expression at the onset of tapetal PCD in wheat.

Due to the explosive increase of electric vehicles (EVs) and universal charging stations (CS), achieving fast authentication is an important topic in the vehicle-to-grid (V2G) network at present. Fast authentication cannot only forcefully defend potential adversaries but also can greatly speed up the charging process between EVs and CSs. Although many researchers have realized this problem and proposed some lightweight cryptographic protocols for fast EV charging, desired security features are not entirely satisfied, such as man-in-the-middle attacks, replay attacks, and impersonation attacks. In this article, we propose an ultra super fast authentication protocol for EV charging by utilizing the characteristics of extended chaotic maps. Furthermore, in view of the unsolved security issues mentioned previously, our proposed protocol can provide elaborate solutions to eliminate these possible attacks in a provable manner. Finally, compared with the relevant authentication protocols for V2G network, the communication and computation costs of our protocol are decreased a lot.

The number of sustainability certifications in the wine industry has grown over the past decades. They are distinctly different from organic, biodynamic or other certifications. This paper combines a detailed literature review of related sustainability certifications to understand the trend in wine certification. The methods include a questionnaire of 12 identified wine certifications (including wineries, vineyards or both) around the world that have sustainability in the certification or organization title. These data help elucidate how these sustainability measures were developed, their levels of membership over time, the mechanics to become certified as sustainable and their plans for future certification. Results show strong support from the wine-making industry and compounded growth in certification. Even with the many differences, all certifications encourage an education component and technological advances. The paper compiles hectares and number of vineyards certified globally. The authors find that the certifications differ in mechanics, leading to issues surrounding transferability and possible confusion for the consumer. Other issues include varying cost to certify, lack of transparency of certified information and no cooperation between certification bodies. Given that all of the certifications plan to grow, more research is needed into sustainability certification, especially from the consumer perspective.

As a promising enabler for edge intelligence, Unmanned Aerial Vehicles (UAV) have become more and more important in Mobile Edge Computing Networks (MECN), such as communication, computation, collection and control service supply. Although Age of Information (AoI) minimization is indispensable for fresh information collection and computation in the UAV-aided MECN, some attackers can launch attacks to deteriorate the availability of precious channel resources, such as revealed channel access attacks (CAAs). Moreover, recent research has not considered the system’s active probability and security issues concurrently, e.g., CAA, in the average AoI minimization process. In this paper, to deal with this problem, we consider an AoI-oriented channel access problem under CAA with a game theory viewpoint. Firstly, to obtain a MECN-based AoI indicator under CAA, the system model with active probability consideration is established. Next, the channel access-based AoI minimization problem is formulated from the viewpoint of the Ordinary Potential Game (OPG). Furthermore, two algorithms called AACSD and DCASD are proposed to determine channel access strategies, by which the Nash Equilibrium (NE) solution of the OPG could be reached. Finally, experiments are conducted under homogeneous and heterogeneous parameter settings, and the simulation results evaluate the correctness and effectiveness of our proposals.

Two main revolutions in data management have occurred recently, namely Big Data analytics and NoSQL databases. Even though they have evolved with different purposes, their independent developments complement each other and their convergence would benefit businesses tremendously in making real-t ime decisions using volumes of co mplex data sets that could be both structured and unstructured. While on one hand many software solutions have emerged in supporting Big Data analytics, on the other, many NoSQL database packages have arrived in the market. However, they lack an independent benchmarking and co mparat ive evaluation. The aim of this paper is to provide an understanding of their contexts and an in-depth study to compare the features of four main NoSQL data models that have evolved. The performance comparison of traditional SQL with No SQL databases for Big Data analytics shows that NoSQL database poses to be a better option for business situations that require simplicity, adaptability, high performance analytics and distributed scalability of large data. This paper concludes that the NoSQL movement should be leveraged for Big Data analytics and would coexist with relational (SQL) databases.

THIS PAPER REPORTS ON the emerging findings of the first year of an inquiry-based professional development program called Educational Leadership in Early Childhood Settings (ELECS). The program was funded by the then Early Childhood Policy and Strategic Projects Division of the Department of Education and Early Childhood Development (Victoria, Australia) and delivered under the auspices of the Bastow Institute of Educational Leadership. The intent of the program was to support early childhood educational leaders to mentor early childhood educators in the implementation of the Victorian Early Years Learning and Development Framework (VEYLDF). The paper interweaves some of the initial data drawn from the program evaluations through a review of the early childhood leadership literature. The paper includes examples of participant understandings of themselves as educational leaders and demonstrates how their involvement in the program informed their leadership in relation to the VEYLDF. The paper concludes with a discussion of the outcomes of the program in terms of the participants' changing perceptions of early childhood leadership.

Big data, a recently popular term that refers to a massive collection of very large and complex data sets, is facing serious security and privacy challenges. Due to the typical characteristics of big data, namely velocity, volume and variety associated with large-scale cloud infrastructures and the Internet of Things (IoT), traditional security and privacy mechanisms are inadequate and unable to cope with the rapid data explosion in such a complex distributed computing environment. With big data analytics being widely used by businesses and government for decision making, security risk mitigation plays an important role in big data infrastructures worldwide. Traditional security mechanisms have failed to cope with the scalability, interoperability and adaptability of contemporary technologies that are required for big data. This paper takes an exploratory initial step using first principles to address this gap in literature. Firstly, we establish the current trends in big data comprehensively by identifying eleven Vs as important dimensions of big data, which form the contributing factors having an impact on the impending security problem. Next, we map the eleven Vs to the three phases of big data life cycle in order to unearth the major security and privacy challenges of big data. Finally, the paper provides four practical strategies adapted from contemporary technologies such as data provenance, encryption and access control, data mining and blockchain, identifying their associated real implementation examples. This work would pave way for future research investigations in this important big data security arena.

Smart home automation is expected to improve living standards with the evolution of internet of things (IoT) that facilitate the remote control of residential appliances. There are, however, several factors that require attention for broader successful consumer adoption. This paper focusses on three key barriers: (i) different underlying technologies requiring an integrated voice-based control for ease of use, (ii) lack of trust due to security and privacy concerns, and (iii) unawareness of the use of machine intelligence by users for exploiting the full potential of smartness. Voice-controlled home environments are possible with cloud-based solutions that are being deployed commercially. However, there are drawbacks due to non-standard voice channels and commands with delays in meeting the required response time for real-time services. Adoption is also required to meet with the expected goals of simplicity, security, and integration. To address these barriers, we propose a model integrating IoT services and wireless technologies for developing a secure smart home automation with a voice-controlled artificial intelligence system. We demonstrate the model’s application in a variety of practical use cases, by implementing a secure and smart voice-based system for an integrated control of several home devices seamlessly.

Light pruning and deficit irrigation regimes are practices which are widely used in high yielding commercial vineyards in the warm climate regions of Australia. Little information is available on their impacts on carbohydrate dynamics in vegetative organs within and between seasons, and on the resulting plant capacity to maintain productivity and ripen fruits. This study was conducted to address this gap in knowledge over five vintages on Vitis vinifera L. cv. Cabernet Franc, Shiraz, and Cabernet Sauvignon in the Sunraysia region of Victoria, Australia. Lighter pruning did not change the total carbohydrates concentration and composition in wood and roots within seasons in Cabernet Franc and Shiraz. However, the total carbohydrate pool (starch and soluble sugars) at the end of dormancy increased under lighter pruning, due to higher vine size, associated with retention and growth of old-wood (trunk and cordons). Water deficit negatively impacted trunk and leaf starch concentrations, over the day and within seasons in Cabernet Sauvignon. Soluble sugars concentrations in these tissues tended to be higher under limited water supply, possibly due to higher sugar mobilization as photosynthesis decreased. Trunk carbohydrate concentrations markedly varied within and between seasons, highlighting the importance of interactive factors such as crop load and climate on carbon status. The period between fruit-set and véraison was shown to be critical for its impact on the balance between carbon accretion and depletion, especially under water deficit. The lower leaf and trunk starch concentration under water deficit resulted in a decrease of yield components at harvest, while similar yields were reached for all pruning systems. The sugar allocated to berries at harvest remained remarkably stable for all practices and seasons, irrespective of vine yield and carbohydrate status in vegetative organs in Shiraz and Cabernet Sauvignon.