- Semantic Web and Ontologies
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Service-Oriented Architecture and Web Services
- Web Applications and Data Management
- Video Analysis and Summarization
- Natural Language Processing Techniques
- Data Quality and Management
- Advanced Database Systems and Queries
- Multimedia Communication and Technology
- Information and Cyber Security
- Web Data Mining and Analysis
- Digital and Cyber Forensics
- Scientific Computing and Data Management
- 3D Shape Modeling and Analysis
- Internet Traffic Analysis and Secure E-voting
- Digital Media Forensic Detection
- Image Retrieval and Classification Techniques
- Computer Graphics and Visualization Techniques
- Mobile and Web Applications
- Smart Grid Security and Resilience
- Metaheuristic Optimization Algorithms Research
- Engineering and Information Technology
- IoT and Edge/Fog Computing
- Data Management and Algorithms
Edith Cowan University
2012-2025
Market Intelligence Strategy Centre (Australia)
2021
ORCID
2020
University of South Australia
2018-2019
Flinders University
2015-2018
South Australia Pathology
2011-2015
Packet analysis is a primary traceback technique in network forensics, which, providing that the packet details captured are sufficiently detailed, can play back even entire traffic for particular point time. This be used to find traces of nefarious online behavior, data breaches, unauthorized website access, malware infection, and intrusion attempts, reconstruct image files, documents, email attachments, etc. sent over network. paper comprehensive survey utilization analysis, including deep...
Cybersecurity issues constitute a key concern of today’s technology-based economies. has become core need for providing sustainable and safe society to online users in cyberspace. Considering the rapid increase technological implementations, it turned into global necessity attempt adapt security countermeasures, whether direct or indirect, prevent systems from cyberthreats. Identifying, characterizing, classifying such threats their sources is required cyber-ecosystem. This paper focuses on...
Abstract Cybersecurity knowledge graphs, which represent cyber-knowledge with a graph-based data model, provide holistic approaches for processing massive volumes of complex cybersecurity derived from diverse sources. They can assist security analysts to obtain cyberthreat intelligence, achieve high level cyber-situational awareness, discover new cyber-knowledge, visualize networks, flow, and attack paths, understand correlations by aggregating fusing data. This paper reviews the most...
Adversaries may exploit a range of vulnerabilities in Internet Things (IoT) environments. These are typically exploited to carry out attacks, such as denial-of-service (DoS) either against the IoT devices themselves, or using perform attacks. attacks often successful due nature protocols used IoT. One popular protocol for machine-to-machine communications is Message Queueing Telemetry Protocol (MQTT). Countermeasures MQTT include testing defenses with existing datasets. However, there lack...
Abstract Expressing machine-interpretable statements in the form of subject-predicate-object triples is a well-established practice for capturing semantics structured data. However, standard used representing these triples, RDF, inherently lacks mechanism to attach provenance data, which would be crucial make automatically generated and/or processed data authoritative. This paper critical review models, annotation frameworks, knowledge organization systems, serialization syntaxes, and...
Anomaly detection from Big Cybersecurity Datasets is very important; however, this a challenging and computationally expensive task. Feature selection (FS) an approach to remove irrelevant redundant features select subset of features, which can improve the machine learning algorithms’ performance. In fact, FS effective preprocessing step anomaly techniques. This article’s main objective quantify accuracy scalability both supervised unsupervised effort, novel using FS, called Detection Using...
Abstract In parallel with the exponentially growing number of computing devices and IoT networks, data storage processing requirements digital forensics are also increasing. Therefore, automation is highly desired in this field, yet not readily available, many challenges remain, ranging from unstructured forensic derived diverse sources to a lack semantics defined for investigation concepts. By formally describing concepts properties, purpose‐designed ontologies enable integrity checking via...
Abstract A massive amount of data is generated with the evolution modern technologies. This high-throughput generation results in Big Data, which consist many features (attributes). However, irrelevant may degrade classification performance machine learning (ML) algorithms. Feature selection (FS) a technique used to select subset relevant that represent dataset. Evolutionary algorithms (EAs) are widely search strategies this domain. variant EAs, called cooperative co-evolution (CC), uses...
Honeypots are progressively becoming a fundamental cybersecurity tool to detect, prevent and record new threats attack methodologies used by attackers penetrate systems. The current technology is advancing rapidly; with the use of virtualisation, most recently, virtual containers, deployment honeypots has become increasingly easier. A varied collection open source such as Cowrie available today, which can be easily downloaded deployed within minutes-with default settings. medium-interaction...
Considering the billions of Internet Things (IoT) devices around world, IoT has brought convenience to people's lives, but also created a larger attack surface. Therefore, specific attention should be paid IoT, especially from two aspects, namely, security and forensics. Security properties, authentication, ensure integrity large amounts data processed in networks, while forensic investigations can identify, collect, retain evidence when abuse systems occurs. Regarding these critical this...
In parallel with the tremendously increasing number of video contents on Web, many technical specifications and standards have been introduced to store details describe content of, add subtitles to, online videos. Some these are based unstructured data limited machine-processability, reuse, interoperability, while others XML-based, representing semi-structured data. While low-level features can be derived automatically, high-level mainly related a particular knowledge domain heavily rely...
3D models play an important role in a wide range of applications from engineering to training, visualization entertainment. The formal representation of, and reasoning over, concepts properties associated with can contribute next-generation scene understanding, classification, indexing, retrieval via characteristics as opposed keywords traditional methods. This paper introduces novel model indexing method X3D-alignment, emphasis on the representation, annotation, efficient content-based...
The conceptualization of domains depicted in videos is a necessary, but not sufficient requirement for reasoning-based high-level scene interpretation, which requires the formal representation timeline structure, moving regions interest, and video production standards, facilities, procedures as well. Multimedia ontologies, including very few however, are exhaustive terms concept coverage, redefine against Semantic Web best practices, aligned with do define complex roles role...
The rapid progress of modern technologies generates a massive amount high-throughput data, called Big Data, which provides opportunities to find new insights using machine learning (ML) algorithms. Data consist many features (also attributes); however, not all these are necessary or relevant, and they may degrade the performance ML Feature selection (FS) is an essential preprocessing step reduce dimensionality dataset. Evolutionary algorithms (EAs) widely used search for FS. Using...
Abstract Due to the volume, variety, and veracity of network data available, information fusion reasoning techniques are needed support analysts’ cyber-situational awareness. These rely on formal knowledge representation define semantics with provenance at various levels granularity. To this end, paper proposes Communication Network Topology Forwarding Ontology, a state-of-the-art ontology that enables formal, unified complex concepts regardless type source. The implementation allows...