M.A.P. Chamikara

The Commonwealth Scientific and Industrial Research Organisation | CSIRO · Data61

Tabular data sharing serves as a common method for data exchange. However, sharing sensitive information without adequate privacy protection can compromise individual privacy. Thus, ensuring privacy-preserving data sharing is crucial. Differential privacy (DP) is regarded as the gold standard in data privacy. Despite this, current DP methods tend t...

Generative AI (e.g., Generative Adversarial Networks - GANs) has become increasingly popular in recent years. However, Generative AI introduces significant concerns regarding the protection of Intellectual Property Rights (IPR) (resp. model accountability) pertaining to images (resp. toxic images) and models (resp. poisoned models) generated. In th...

We propose a hierarchical blockchain-based platform for ensuring the integrity of smart city Internet-of-Things (IoT) data and blockchain interoperability in this paper. The well-defined structural hierarchy of managing organizations in a smart city face several data management issues. The integration of emerging technologies, such as (IoT), has in...

Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially...

Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover...

Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep learning is widely utilized for face recognition (FR); however, such models are vulnerable to backdoor attacks e...

Federated learning (FL) is a collaborative learning approach that has gained much attention due to its inherent privacy preservation capabilities. However, advanced adversarial attacks such as membership inference and model memorization can still make FL vulnerable and potentially leak sensitive private data. Literature shows a few attempts to alle...

Passwords are regarded as the most common authentication mechanism used by Web-based services, despite large-scale attacks and data breaches regularly exploiting password-associated vulnerabilities. We investigate the trends behind password formulation in an exploratory study to postulate that social identity and language play a major role in users...

Different assessment models exist to measure a coun-try's cyber security maturity levels. These levels serve as a benchmark for indicating how well prepared a nation is against a cyber security attack and how resilient it would be in recovering from such an attack. However, results from these maturity assessments are either too general, overly comp...

In the distributed collaborative machine learning (DCML) paradigm, federated learning (FL) recently attracted much attention due to its applications in health, finance, and the latest innovations such as industry 4.0 and smart vehicles. FL provides privacy-by-design. It trains a machine learning model collaboratively over several distributed client...

It is a well-known fact that there are often side effects to the long-term use of certain medications. These side effects can vary from mild dizziness to, at its most serious, death. The main factors that cause these side effects are the chemical composition, the mode of treatment, and the dose. The dynamics that govern the reaction of a drug heavi...

Personally identifiable information (PII) can find its way into cyberspace through various channels, and many potential sources can leak such information. Data sharing (e.g. cross-agency data sharing) for machine learning and analytics is one of the important components in data science. However, due to privacy concerns, data should be enforced with...

The advancements in positioning technologies have led to the emergence of various location-based services, resulting in a drastic increase in location-based data generation, producing big-data. Location data are often linked with user privacy, as they can reveal sensitive information such as the places visited by a person. Moreover, most location-b...

Edge computing and distributed machine learning have advanced to a level that can revolutionize a particular organization. Distributed devices such as the Internet of Things (IoT) often produce a large amount of data, eventually resulting in big data that can be vital in uncovering hidden patterns, and other insights in numerous fields such as heal...

In the distributed collaborative machine learning (DCML) paradigm, federated learning (FL) recently attracted much attention due to its applications in health, finance, and the latest innovations such as industry 4.0 and smart vehicles. FL provides privacy-by-design. It trains a machine learning model collaboratively over several distributed client...

This study intends to identify the most prevalent sources of child malnutrition in the estate sector/plantation sector in Sri Lanka. It seeks to examine the relevance of what has been identified as ‘socio-economic determinants’ of child malnutrition in national-level surveys.

In the distributed collaborative machine learning (DCML) paradigm, federated learning (FL) recently attracted much attention due to its applications in health, finance, and the latest innovations such as industry 4.0 and smart vehicles. FL provides privacy-by-design. It trains a machine learning model collaboratively over several distributed client...

Personally identifiable information (PII) can find its way into cyberspace through various channels, and many potential sources can leak such information. To preserve user privacy, researchers have devised different privacy-preserving approaches; however, the usability of these methods, in terms of practical use, needs careful analysis due to the h...

Facial recognition technologies are implemented in many areas, including but not limited to, citizen surveillance, crime control, activity monitoring, and facial expression evaluation. However, processing biometric information is a resource-intensive task that often involves third-party servers, which can be accessed by adversaries with malicious i...

Facial recognition technologies have become popular and implemented in many areas, including but not limited to, citizen surveillance, crime control, activity monitoring, and facial expression evaluation. However, processing biometric information is a resource-intensive task that often involves third-party servers, which can be accessed by adversar...

Federated learning (FL) and split learning (SL) are two recent distributed machine learning (ML) approaches that have gained attention due to their inherent privacy-preserving capabilities. Both approaches follow a model-to-data scenario, in that an ML model is sent to clients for network training and testing. However, FL and SL show contrasting st...

Edge computing and distributed machine learning have advanced to a level that can revolutionize a particular organization. Distributed devices such as the Internet of Things (IoT) often produce a large amount of data, eventually resulting in big data that can be vital in uncovering hidden patterns, and other insights in numerous fields such as heal...

Industrial internet of things (IIoT) is revolutionizing many leading industries such as energy, agriculture, mining, transportation, and healthcare. IIoT is a major driving force for Industry 4.0, which heavily utilizes machine learning (ML) to capitalize on the massive interconnection and large volumes of IIoT data. However, ML models that are tra...

This paper proposes a new line clipping algorithm against a convex polygon with 𝑂(𝑁) time complexity. The line segment is pruned against each extended edge of the polygon as the first step of the proposed algorithm. Then, the pruning process gives accurate outcomes for completely inside and partially inside line segments only. The algorithm was dev...

National culture and cybersecurity maturity (CM) both play defining roles in the identity and security of a nation. This study examines the relationship that these two constructs play in determining whether certain cultural dimensions of a nation leads to riskier cybersecurity behaviours. Based on the confirmed affirmation of the relationship betwe...

The internet of things (IoT) is transforming major industries including but not limited to healthcare, agriculture, finance, energy, and transportation. IoT platforms are continually improving with innovations such as the amalgamation of software-defined networks (SDN) and network function virtualization (NFV) in the edge-cloud interplay. Deep lear...

Deep learning (DL) is a promising area of machine learning which is becoming popular due to its remarkable accuracy when trained with a massive amount of data. Often, these datasets are highly sensitive crowd-sourced data such as medical data, financial data, or image data, and the DL models trained on these data tend to leak privacy. We propose a...

A vast amount of valuable data is produced and is becoming available for analysis as a result of advancements in smart cyber-physical systems. The data comes from various sources, such as healthcare, smart homes, smart vehicles, and often includes private, potentially sensitive information that needs appropriate sanitization before being released f...

In this paper, we present a novel architecture of blockchain-based tamper-proof electronic health record (EHR) management system. Recording electronic health data in cloud-based storage systems always pose a threat to information security. Intruders can delete or tamper EHR of patients, giving benefits to insurance companies or hiding medical malpr...

A vast amount of valuable data is produced and is becoming available for analysis as a result of advancements in smart cyber-physical systems. The data comes from various sources, such as healthcare, smart homes, smart vehicles, and often includes private, potentially sensitive information that needs appropriate sanitization before being released f...

Computing technologies pervade physical spaces and human lives, and produce a vast amount of data that is available for analysis. However, there is a growing concern that potentially sensitive data may become public if the collected data are not appropriately sanitized before being released for investigation. Although there are more than a few priv...

Computing technologies pervade physical spaces and human lives, and produce a vast amount of data that is available for analysis. However, there is a growing concern that potentially sensitive data may become public if the collected data are not appropriately sanitized before being released for investigation. Although there are more than a few priv...

The widespread use of the Internet of Things (IoT) has raised many concerns, including the protection of private information. Existing privacy preservation methods cannot provide a good balance between data utility and privacy, and also have problems with efficiency and scalability. This paper proposes an efficient data stream perturbation method (...

Vacuum cleaners play a key role in making the human lives easier. But the existing vacuum cleaning systems show low efficiency and less accuracy. This paper discusses the possibility of using an integrated system of vacuum cleaners which can work in a synchronous manner to increase the efficiency of the process. The proposed method investigates the...

It is a well-known fact that some criminals follow perpetual methods of operations known as modi operandi. Modus operandi is a commonly used term to describe the habits in committing crimes. These modi operandi are used in relating criminals to crimes for which the suspects have not yet been recognized. This paper presents the design, implementatio...

Increasing trend of grave crimes in a society indicates that the security agencies have to shoulder the burden of criminals in larger numbers than the past. A considerable number of criminals have already been convicted and imprisoned, and some of them have been released after completing their imprisonment and are under supervision. The advancement...

It is a well-known fact that some criminals follow perpetual methods of operations, known as modus operandi (MO) which is commonly used to describe the habits in committing something especially in the context of criminal investigations. These modus operandi are then used in relating criminals to other crimes where the suspect has not yet been recog...

It is a well-known fact that some criminals follow perpetual methods of operations, known as modus operandi (MO) which is commonly used to describe the habits in committing something especially in the context of criminal investigations. These modus operandi are then used in relating criminals to other crimes where the suspect has not yet been recog...

The manual crime recording and investigation systems in police stations all around the world are generating piles of crime documents which make storage and retrieval of reliable crime information extremely difficult as well as inefficient. Furthermore, investigators of central authorities have to manually search through these documents and communic...

The manual crime recording and investigation systems in police stations all around the world are generating piles of crime documents which make storage and retrieval of reliable crime information extremely difficult as well as inefficient. Furthermore, investigators of central authorities have to manually search through these documents and communic...

Understanding community structure helps to interpret the role of actors in a social network. Actor has close ties to actors within a community than actors outside of its community. Community structure reveals important information such as central members in communities and bridges members who connect communities. Clustering algorithms like hierarch...

Character recognition techniques for printed documents are widely used for English language. However, the systems that are implemented to recognize Asian languages struggle to increase the accuracy of recognition. Among other Asian languages (such as Arabic, Tamil, Chinese), Sinhala characters are unique, mainly because they are round in shape. Thi...

Noise removal from images is an important activity for successful processing of images. The main objective of this research work is to investigate the applicability of soft computing techniques and statistical techniques for noise filtering. This paper presents a novel method for noise filtering in images using a fuzzy based statistical method. Thi...

This paper presents a statistical analysis in the sociological perspective for the grave crime occurrences from the year 2005 to 2011 in Sri Lanka. Graphical interpretations of the datasets showed some significant occurrences of five major grave crime types which can be listed as House Breaking (HB), Hurt by Knife (HK), Robbery (RB), Theft (TH), Ch...

Identifying patterns in Sinhala characters is a very difficult task because the similarities between the Sinhala characters lie in a very mild extent. Printed documents and hand written character recognition play a major role in many areas like security, defence, business and so forth. However, identifying hand written Sinhala characters is difficu...

Fuzzy set theory has become a fashionable theory used in many branches of real life such as dynamics systems, biological phenomena etc. The concepts of fuzzy numbers, arithmetic operations and necessary calculus of fuzzy functions for developing of fuzzy analysis were first introduced and investigated by Zadeh. For the development of calculus fo...

Construction of block designs is an important part of design theory. Literature shows that there are several ways of constructing block designs with parameters(𝑣, 𝑘, 𝜆). Further, the correspondence between Hadamard matrices and block designs is well known. One can obtain a (𝑣, 𝑘, 𝜆)−design from Hadamard matrices and vice versa. These designs hav...

This paper discusses the socio-economical challenges faced by the war widows in Sri Lanka in the context of post-war development scenario, from a social perspective.

This research introduces a new set of 32 in-equivalent Hadamard matrices of order 404 of Goethals Seidel type. To apply the Goethals Seidel method, four Turyn type sequences of lengths 34 are found by a computer search. These sequences are used to construct base sequences of lengths 67 and are used to generate a set of four T-sequences of length 10...

Mobile communications has become one of the fastest growing sectors in the world today. With the technological advancement, mobile communication has subjected to many upgrades such as 2G, 3G, 4G. The question of “Does a customer get the expected capabilities from it?” is not answered yet. Even though, the subscribers of all operators pay almo...

The Hadamard conjecture is that Hadamard matrices exist for all orders 1,2,4t where t≥1 is an integer. The most compatible way of constructing Hadamard matrices is to use the Kronecker product whenever there exist a Hadamard matrix of order t above. Otherwise, the most convenient way to develop a Hadamard matrix is to use certain sequences of zeros...

The Hadamard conjecture is the statement that Hadamard matrices exist for all orders where is an integer.The most compatible way of constructing Hadamard matrices is to use the Kronecker product whenever there exists a Hadamard matrix of order above. Otherwise, the most convenient way to develop a Hadamard matrix is to use certain sequences of...

This paper presents an algorithm for efficient detection of the nearest police station for a specific position(coordinates). The algorithm is based on Geographic Information System (GIS), Geographic Positioning Systems (GPS) and the J48 classification algorithm. In other words, the proposed algorithm is an effective integration of these three. The...

Literature shows that there are several ways of generating Latin squares, but there is not enough implementation about Super-symmetric Latin squares. This paper proposes a mathematical algorithm to construct Super-symmetric Latin squares of order 2 ୬ by substituting blocks of order 2 n which has the basic properties of a recursive algorithm. The pr...

It is observed that law enforcement authorities all around the world lack a good and efficient crime analysis system facilitated by the new advancement of information technology. The globalization and increasing complexity of crime patterns have made the analysis of crime date even difficult. Sri Lanka's police too have been dealing with these diff...

Information technology (IT) has become one of the most innovative subjects in human life today. IT is applied to almost all the fields making it more independent from the ethic of use. Mobile services have become one of the leading areas where IT is thoroughly used. With the application of IT, mobile network providers has been capable of upgrading...

This paper proposes an algorithm which can be used to construct strongly regular graphs from Hadamard matrices.A graph is strongly regular if there are integers and such that every two adjacent vertices have common neighbours and every two non adjacent vertices have common neighbors. Proposed method is mainly based on basic matrix manipulations. If...

The Walsh-Hadamard transform (WHT) is an orthogonal transformation that decomposes a signal into a set of orthogonal, rectangular waveforms called Walsh functions. The transformation has no multipliers and is real because the amplitude of Walsh (or Hadamard) functions has only two values, +1 or -1.Therefore WHT can be used in many different applica...