Leslie F. Sikos

Leslie F. Sikos
Edith Cowan University | ECU · School of Science

Ph.D.

About

127
Publications
48,744
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
872
Citations
Citations since 2017
54 Research Items
754 Citations
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
Introduction
Leslie F. Sikos, Ph.D., is a computer scientist specializing in cybersecurity applications powered by artificial intelligence and data science.

Publications

Publications (127)
Book
This book presents a collection of state-of-the-art AI approaches to cybersecurity and cyberthreat intelligence, offering strategic defense mechanisms for malware, addressing cybercrime, and assessing vulnerabilities to yield proactive rather than reactive countermeasures. The current variety and scope of cybersecurity threats far exceed the capabi...
Book
This book presents a collection of state-of-the-art approaches to utilizing machine learning, formal knowledge bases and rule sets, and semantic reasoning to detect attacks on communication networks, including IoT infrastructures, to automate malicious code detection, to efficiently predict cyberattacks in enterprises, to identify malicious URLs an...
Article
Full-text available
Packet analysis is a primary traceback technique in network forensics, which, providing that the packet details captured are sufficiently detailed, can play back even the entire network traffic for a particular point in time. This can be used to find traces of nefarious online behavior, data breaches, unauthorized website access, malware infection,...
Chapter
Cyber-situational awareness is crucial to applications such as network monitoring and management, vulnerability assessment, and defense. To gain improved cyber-situational awareness, analysts can benefit from automated reasoning-based frameworks. However, such frameworks would require the processing of enormous amounts of network data, which are ch...
Article
Full-text available
Cybersecurity knowledge graphs, which represent cyber-knowledge with a graph-based data model, provide holistic approaches for processing massive volumes of complex cybersecurity data derived from diverse sources. They can assist security analysts to obtain cyberthreat intelligence, achieve a high level of cyber-situational awareness, discover new...
Article
Full-text available
The explosion of online video streaming in recent years resulted in advanced services both in terms of efficiency and convenience. However, Internet-connected video cameras are prone to exploitation, leading to information security issues and data privacy concerns. The proliferation of video-capable Internet of Things devices and cloud-managed surv...
Chapter
The continued and rapid development of Internet of Things (IoT) devices in our modern world has brought significant changes to how society is being productive and connected. The widespread uptake and application of IoT devices in the past 10 years alone has seen how technology has advanced to aid in our daily lives and is now considered an integral...
Conference Paper
Conpot is a low-interaction SCADA honeypot system that mimics a Siemens S7-200 proprietary device on default deployment. Honeypots operating using standard configurations can be easily detected by adversaries using scanning tools such as Shodan. This study focuses on the capabilities of the Conpot honeypot, and how these competences can be used to...
Research
Full-text available
Anomaly detection from Big Cybersecurity Datasets is very important; however, this is a very challenging and computationally expensive task. Feature selection (FS) is an approach to remove irrelevant and redundant features and select a subset of features, which can improve the machine learning algorithms’ performance. In fact, FS is an effective pr...
Article
In recent times, cyberattacks on the Internet of Health Things (IoHT) have continuously been growing, and so it is important to develop robust countermeasures. However, there is a lack of publicly available datasets reflecting cyberattacks on IoHT, mainly due to privacy concerns. This paper showcases the development of a dataset, ECU-IoHT, which bu...
Chapter
Cowrie is a medium-interaction SSH, and Telnet honeypot used to record brute force attacks and SSH requests. Cowrie utilizes a Python codebase, which is maintained and publicly available on GitHub. Since its source code is publicly released, not only security specialists but cybercriminals can also analyze it. Nonetheless, cybersecurity specialists...
Conference Paper
Cowrie is a medium-interaction SSH, and Telnet honeypot used to record brute force attacks and SSH requests. Cowrie utilizes a Python codebase, which is maintained and publicly available on GitHub. Since its source code is publicly released, not only security specialists but cybercriminals can also analyze it. Nonetheless, cybersecurity specialists...
Article
Full-text available
An amendment to this paper has been published and can be accessed via the original article.
Article
Full-text available
A massive amount of data is generated with the evolution of modern technologies. This high-throughput data generation results in Big Data, which consist of many features (attributes). However, irrelevant features may degrade the classification performance of machine learning (ML) algorithms. Feature selection (FS) is a technique used to select a su...
Chapter
The many benefits of knowledge graphs using or based on the Resource Description Framework (RDF) well justify the utilization and wide deployment of a simple yet powerful, formally grounded data model, its serialization formats, vocabulary, and well-defined interpretation to be used for efficient querying, data integration, and automated reasoning....
Chapter
Interpreting cyber-knowledge is challenging due to the data heterogeneity issues typical to data aggregation from disparate data sources. This chapter demonstrates knowledge graph-based techniques to capture and reason over provenance for communication networks at different levels of granularity, thereby getting the best of both worlds, structured...
Article
Full-text available
Expressing machine-interpretable statements in the form of subject-predicate-object triples is a well-established practice for capturing semantics of structured data. However, the standard used for representing these triples, RDF, inherently lacks the mechanism to attach provenance data, which would be crucial to make automatically generated and/or...
Article
Full-text available
Cybersecurity issues constitute a key concern of today’s technology-based economies. Cybersecurity has become a core need for providing a sustainable and safe society to online users in cyberspace. Considering the rapid increase of technological implementations, it has turned into a global necessity in the attempt to adapt security countermeasures,...
Article
In parallel with the exponentially growing number of computing devices and IoT networks, the data storage and processing requirements of digital forensics are also increasing. Therefore, automation is highly desired in this field, yet not readily available, and many challenges remain, ranging from unstructured forensic data derived from diverse sou...
Article
Full-text available
The rapid progress of modern technologies generates a massive amount of high-throughput data, called Big Data, which provides opportunities to find new insights using machine learning (ML) algorithms. Big Data consist of many features (also called attributes); however, not all these are necessary or relevant, and they may degrade the performance of...
Conference Paper
There is an increasing awareness of the cybersecurity issues around SCADA/ICS systems that are the cyber-physical connectors of our industrialized world to the Internet. Alerton’s BACtalk VAV-DD controller is an example of a multipurpose SCADA device that provides autonomous pressure control for any dual-duct VAV container using the BACnet protocol...
Chapter
Considering the complexity and dynamic nature of cyberthreats, the automation of data-driven analytics in cyberthreat intelligence is highly desired. However, the terminology of cyberthreat intelligence varies between methods, techniques, and applications, and the corresponding expert knowledge is not codified, making threat data inefficient, and s...
Chapter
Full-text available
The implementation of virtual and augmented reality environments on the web requires integration between 3D technologies and web technologies, which are increasingly focused on collaboration, annotation, and semantics. Thus, combining VR and AR with the semantics arises as a significant trend in the development of the web. The use of the Semantic W...
Conference Paper
Honeypots are progressively becoming a fundamental cybersecurity tool to detect, prevent and record new threats and attack methodologies used by attackers to penetrate systems. The current technology is advancing rapidly; with the use of virtualisation, and most recently, virtual containers, the deployment of honeypots has become increasingly easie...
Conference Paper
Full-text available
One of the main obstacles for wide dissemination of immersive virtual and augmented reality environments on the Web is the lack of integration between 3D technologies and web technologies , which are increasingly focused on collaboration, annotation and semantics. This gap can be filled by combining VR and AR with the Semantic Web, which is a signi...
Chapter
For network analysts, understanding how network devices are interconnected and how information flows around the network is crucial to the cyber-situational awareness required for applications such as proactive network security monitoring. Many heterogeneous data sources are useful for these applications, including router configuration files, routin...
Chapter
Network vulnerability checking, automated cyberthreat intelligence, and real-time cybersituational awareness require task automation that benefit from formally described conceptual models. Knowledge organization systems, including controlled vocabularies, taxonomies, and ontologies, can provide the network semantics needed to turn raw network data...
Article
Full-text available
Due to the volume, variety, and veracity of network data available, information fusion and reasoning techniques are needed to support network analysts’ cyber-situational awareness. These techniques rely on formal knowledge representation to define the network semantics with data provenance at various levels of granularity. To this end, this paper p...
Conference Paper
The overwhelming and constantly growing amount of data network analysts have to process urges automated mechanisms for cyberthreat intelligence. The formal representation of network knowledge unifies data from diverse sources, and enables efficient automation via reasoning, however, network data is inherently uncertain and/or imprecise. There are v...
Article
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 of the timeline structure, the moving regions of interest, and video production standards, facilities, and procedures as well. Multimedia ontologies, includi...
Article
Because of the growing popularity of 3D modelling, there is a great demand for efficient mechanisms to automatically process 3D contents. Owing to the lack of semantics, however, most 3D scenes cannot be interpreted by software agents. 3D ontologies can provide formal definitions for 3D objects; however, many of them are semi-structured only, cover...
Conference Paper
Ontology-based representation of video scenes and events indicates a promising direction in content-based video retrieval. However, the multimedia ontologies described in the literature often lack formal grounding, and none of them are suitable for representing complex video scenes. This issue can be partially addressed using SWRL rules, which, how...
Conference Paper
There is an overwhelming variety of multimedia ontologies used to narrow the semantic gap, many of which are overlapping, not richly axiomatized, do not provide a proper taxonomical structure, and do not define complex correlations between concepts and roles. Moreover, not all ontologies used for image annotation are suitable for video scene repres...
Chapter
The constantly increasing popularity and ubiquity of videos urges efficient automated mechanisms for processing video contents, which is a big challenge due to the huge gap between what software agents can obtain from signal processing and what humans can comprehend based on cognition, knowledge, and experience. Automatically extracted low-level vi...
Article
Because of the growing popularity of 3D modeling, there is a great demand for efficient mechanisms to automatically process 3D contents. Due to the lack of semantics, however, most 3D scenes cannot be interpreted by software agents. 3D ontologies can provide formal definitions for 3D objects, however, many of them are semistructured only, cover a n...
Chapter
The contents of multimedia resources are often not machine-interpretable due to the number of potential interpretations, limited training dataset, poor noise-signal ratio, occlusion, compression artifacts, and the lack of common sense knowledge. The low-level feature descriptors utilized in machine learning usually do not correspond directly to the...
Chapter
Description logics (DL) constitute a family of formal knowledge representation languages used for ontology grounding, each of which comes with well-understood computational properties. A crucial design principle in description logics is to establish a favorable trade-off between expressivity and scalability and, when needed, maximize expressivity....
Book
This book illustrates how to use description logic-based formalisms to their full potential in the creation, indexing, and reuse of multimedia semantics. To do so, it introduces researchers to multimedia semantics by providing an in-depth review of state-of-the-art standards, technologies, ontologies, and software tools. It draws attention to the i...
Conference Paper
3D models play an important role in a wide range of applications from engineering to training, from visualization to entertainment. The formal representation of, and reasoning over, concepts and properties associated with 3D models can contribute to next-generation 3D scene understanding, classification, indexing, and retrieval via 3D characteristi...
Chapter
The automated processing of multimedia resources is challenging, mainly due to the huge gap between what computers can interpret and what humans understand, known as the Semantic Gap. Automatically extractable low-level features, such as dominant color or color distribution, are suitable for a limited range of practical applications only, and are n...
Chapter
The formal representation of depicted concepts and events makes it possible to infer new, implicit statements. For multimedia contents, reasoning enables automated scene interpretation, advanced classification and indexing, and customized data querying. Several reasoning services have been defined and investigated for a variety of description logic...
Chapter
A large share of digital contents is human-readable only, thus not suitable for automated processing and inefficient when searching for related information. Traditional web datasets can be considered as isolated data silos that are not linked to each other. This limitation can be addressed by organizing and publishing data using powerful formats th...
Chapter
The methods and methodologies for building ontologies, called ontology engineering, include ontology development, ontology transformation, ontology merging, ontology integration, ontology mapping, and ontology alignment. During ontology development, the knowledge domain and the scope to cover are determined, and the relevant concepts and their prop...
Conference Paper
The automated processing of 3D models of cultural artifacts can be significantly improved with formally defined high-level structured descriptors. However, despite the large number of multimedia ontologies, the semantic enrichment of 3D models still has open issues. Many 3D ontologies are semi-structured only, cover a very narrow knowledge domain,...
Article
Video annotation tools are often compared in the literature, however, most reviews mix unstructured, semi-structured, and the very few structured annotation software. This paper is a comprehensive review of video annotations tools generating structured data output for video clips, regions of interest, frames, and media fragments, with a focus on Li...
Conference Paper
Full-text available
Multimedia reasoning, which is suitable for, among others, multimedia content analysis and high-level video scene interpretation, relies on the formal and comprehensive conceptualization of the represented knowledge domain. However, most multimedia ontologies are not exhaustive in terms of role definitions, and do not incorporate complex role inclu...
Conference Paper
Full-text available
In parallel with the tremendously increasing number of video contents on the Web, many technical specifications and standards have been introduced to store technical details and describe the content of, and add subtitles to, online videos. Some of these specifications are based on unstructured data with limited machine-processability, data reuse, a...
Book
A major limitation of conventional web sites is their unorganized and isolated contents, which is created mainly for human consumption. This limitation can be addressed by organizing and publishing data, using powerful formats that add structure and meaning to the content of web pages and link related data to one another. Computers can “understand”...
Chapter
While machine-readable datasets are published primarily for software agents, automatic data extraction is not always an option. Semantic Information Retrieval often involves users searching for the answer to a complex question, based on the formally represented knowledge in a dataset or database. While Structured Query Language (SQL) is used to que...
Chapter
The sustainability of huge and ever-growing data pools using different formats that cannot be processed with traditional software tools is the next big challenge for web designers, Internet marketers, and software engineers and requires new technologies and practices. One of the approaches to cope with Big Data is to use Semantic Web technologies,...
Chapter
To improve the automated processability of web sites, formal knowledge representation standards are required that can be used not only to annotate markup elements for simple machine-readable data but also to express complex statements and relationships in a machine-processable manner. After understanding the structure of these statements and their...
Chapter
The content of conventional web sites is human-readable only, which is unsuitable for automatic processing and inefficient when searching for related information. Web datasets can be considered as isolated data silos that are not linked to each other. This limitation can be addressed by organizing and publishing data, using powerful formats that ad...
Chapter
In this service-oriented world, online services are important parts of web offerings. Online shopping, flight booking, hotel booking, navigation, public transport services, government services, community services, and media services are parts of our daily lives. However, the range of service offerings is widening. In the information technology (IT)...
Chapter
Extracting and manipulating RDF from semistructured data and writing client applications to handle RDF data are common tasks that can be made easier and more efficient using software tools. Web designers and search engine optimization (SEO) experts often generate machine-readable annotations or convert existing structured data to a different serial...
Chapter
By reading the book, you learned how to write HTML5 Microdata and JSON-LD annotations in the markup, develop Semantic Web applications, describe web services in standardized languages, run powerful queries on Linked Open Data (LOD) datasets, and develop Semantic Web applications. Now that you have become familiar with Semantic Web technologies, let...
Chapter
Graph models and algorithms are ubiquitous, due to their suitability for knowledge representation in e-commerce, social media networks, research, computer networks, electronics, as well as for maximum flow problems, route problems, and web searches. Graph databases are databases with Create, Read, Update, and Delete (CRUD) methods exposing a graph...
Chapter
In contracts to the isolated data silos of the conventional Web, the Semantic Web interconnects open data, so that all datasets contribute to a global data integration, connecting data from diverse domains, such as people, companies, books, scientific publications, films, music, reviews, television and radio programs, medicine, statistics, online c...
Chapter
Modern web sites are meant to be dynamic. Very few web sites are based purely on document structure and style sheets. Web site sections often behave differently or react to user input. While small programs can run in the browser, complex functions are usually executed on the web server. Most dynamic sites are powered by databases that are handled b...
Chapter
Since modern markup elements and attributes are becoming more and more sophisticated, complex development software tools are used to generate web pages. Advanced text editors are fundamental programs in the toolbox of every web designer. Advanced text editors can be used for a variety of tasks, and provide very useful features such as syntax highli...
Chapter
Since markup is the essence of web documents, it provides the largest place for standardization efforts. The popularity of HTML has not decreased since the birth of the Web. Becoming familiar with the versions and variants of that language and understanding the differences between HTML and XHTML are crucial for understanding the techniques for chan...
Chapter
The correct appearance and web documents handling cannot be guaranteed simply by applying strict, error-free markup. Web server configuration has a significant impact on web site appearance, operation, and behavior. Documents should be served with the proper media type and character encoding. Content negotiation can be used to serve various documen...
Chapter
Design has always been an important factor in web site development, partly because appearance is responsible for the first impression. If the design of a web site catches the eye, it is more likely that visitors will become customers or clients. Web typography has recently started to attract attention, especially though proper whitespace handling a...
Chapter
The amount of up-to-date information shared on the Internet is constantly growing. Web syndication provides news feed channels in order to publish a summary of recently updated web site contents, latest news, or forum posts. These web feeds make it possible for users to stay informed without browsing web sites. Moreover, the same feed can also be s...
Chapter
Beyond optimal markup and styles provided by the proper implementation of web standards, there are designing conventions that are browser-independent, reliable, and satisfactory, and considered as best practices. It is important to know the techniques that provide standard-compliant code and distinguish them from those tricks and hacks that cause i...
Chapter
A golden rule in web site standardization is to separate content from appearance. External style sheets should be preferred to inline styles except when only a small portion of a web page is styled. The syntax and naming convention of external style sheets and the style attribute values are slightly different. To achieve the highest code quality, t...
Chapter
The various computer languages used on the Web, including but not limited to (X)HTML, CSS, RDF, and RSS, provide structure, style, metadata, semantics, and other document features. Similar to natural languages, they have their own grammar, vocabulary, and syntax that need to be followed. However, just like the grammar, structural, or spelling error...
Chapter
Web documents are published in all languages of the world, using a variety of character repertoires and features such as text direction. Several technologies support multilingual websites. To display characters correctly on websites, a character encoding that supports the required characters should be used to encode the markup files. The character...
Chapter
With the rapid evolution of web services and technologies, the number of Internet users is constantly increasing. Since many people suffer from various temporary or permanent disabilities and deficiencies, advanced web development practices should be applied to provide content that is accessible for all. The importance of web accessibility is being...
Chapter
Several factors should be considered to achieve web site validity. The code is written either manually or generated automatically, and errors are inevitable. Errors occur in the markup, in the style sheet, in the XML files, in scripts, in server settings, and so forth. By analyzing and learning the most common errors, many of them can be eliminated...
Chapter
Being familiar with web technologies and standards is not sufficient for standardizing invalid sites and developing valid sites from scratch. Web site standardization is always a complex project, and it takes into account a variety of requirements simultaneously. The list includes, but is not limited to, full standard compliance; optimal code lengt...
Chapter
Technical standards are widely used in various fields of life—think of the standards of paper size and the standard envelopes that fit them, or AC power plugs and their corresponding sockets. Web standards, similar to other standards, are normative specifications of technologies and methodologies. In other words, they are well-defined sets of requi...
Chapter
The basic structure of web documents provides the desired appearance and functionality. By default, however, the content is human-readable only. You can use additional technologies to provide meaning to web documents, making them machine-readable and human-readable at the same time. There is a wide choice of metadata available, along with microform...
Article
Full-text available
Searching for videos online is inefficient if the search relies exclusively on relevant keywords in the text surrounding the object. HTML5 introduced advanced semantic annotation in the form of a new metadata format called microdata. Along with the video element which provides semantics to embedded video contents, media metadata can also be used to...
Chapter
A golden rule in web site standardization is to separate content from appearance. XHTML elements eliminate style attributes. Style sheets should be provided in external files. Style definitions provided in CSS have similar features to the ones applied in older HTML documents as inline styles. However, naming conventions and additional mechanisms ar...
Chapter
Since modern markup elements and attributes are becoming more and more sophisticated, complex development software is used to generate web pages. However, certain web content such as descriptive metadata can be so complex that it often requires human decisions. Advanced text editors always have a top priority in the software list of every web stand...
Chapter
Technical standards are widely used in various fields of life—think of the standards of paper size and the standard envelopes that fit them. Web standards, similar to other standards, are normative specifications of technologies and methodologies. In other words, they are well-defined sets of requirements to be satisfied. They are not only ideal fr...
Chapter
The various computer languages used on the Web, including but not limited to (X)HTML, CSS, RDF, and RSS, provide structure, style, metadata, semantics, and other document features. Similar to natural languages, they have their own grammar, vocabulary, and syntax that need to be followed. However, just like the grammar, structural, or spelling error...
Chapter
Being familiar with certain technologies and standards is not sufficient for standardizing invalid sites and developing valid sites from scratch. Web site standardization is always a complex project, and it takes into account a variety of needs simultaneously. The list includes, but is not limited to, full standard compliance; optimal code length;...
Chapter
Design has always been an important factor in web site development, partly because appearance is responsible for the first impression. If the design of a web site catches the eye, it is more likely that visitors will become customers or clients. Web typography has recently started to attract attention, especially though proper whitespace handling a...
Chapter
Beyond optimal markup and styles provided by the appropriate use of web standards, there are designing conventions that are browser-independent, reliable, and satisfactory, which thus can be applied as ultimate solutions. Best practices should have top priority in web site development. Although they change over time, many can be applied for years....
Chapter
The correct appearance and handling of web documents cannot be guaranteed simply by applying strict, error-free markup. Web server configuration has a significant impact on web site appearance, operation, and behavior. Documents should be served with the proper media type and character encoding. Content negotiation can be used to serve various docu...
Chapter
Since markup is the essence of web documents, it provides the largest place for standardization efforts. The popularity of HTML has not decreased since the birth of the Web; thus, becoming familiar with the versions and variants of that language is important. On the other hand, the application of XML languages has been increasing significantly. The...
Chapter
Web authors publish in all languages of the world, and several technologies support this multilingual Web. A key factor of correct character representation on the Web is applying the appropriate character encoding. Although this depends on server settings as well, web developers can effectively contribute to proper internationalization of the physi...
Chapter
The amount of up-to-date information shared on the Internet is constantly growing. Web syndication provides news feed channels in order to publish a summary of recently updated web site contents, latest news, or forum posts. These web feeds make it possible for users to stay informed without browsing web sites. Moreover, the same feed can also be s...
Chapter
Several factors should be considered to achieve web site validity. The code is written either manually or generated automatically, and errors are inevitable. This is also true for server settings. Errors occur in the markup, in the style sheet, in the XML files, in scripts, and so forth. By analyzing and learning the most common errors, many of the...
Chapter
With the rapid evolution of web services and technologies, the number of Internet users is constantly increasing. Since many people suffer from various temporary or permanent disabilities and deficiencies, advanced web development practices should be applied to provide content that is accessible for all. The importance of web accessibility is being...
Chapter
The basic structure of web documents provides the desired appearance and functionality. By default, however, the content is human-readable only. You can use additional technologies to provide meaning to web documents, making them machine-readable and part of the Semantic Web. Many terms have been recently introduced for emerging Semantic Web techno...

Network

Cited By