Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
5 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Assessing the Efficacy of Machine Learning Algorithms in Predicting Critical Properties of Gold Nanoparticles for Pharmaceutical Applications(Springer, 2025-07-08) Fernando, H; Mohottala, S; Jayanetti, M; Thambiliyagodage, CAu nanoparticles are increasingly used in pharmaceuticals, but their synthesis is costly and time-intensive. Machine Learning can help optimize this process. In this research, eight distinct Machine Learning models were implemented and optimized on a dataset comprising 3000 records of gold nanoparticles. The performance of these models was assessed using four accuracy metrics and the time required for training and inference. The results are promising, with all seven models demonstrating high accuracy and low time requirements. Notably, the XGBoost and Artificial Neural Network models exhibited exceptional performance, with Mean Squared Error values of 0.0235 and 0.0098, Mean Absolute Error values of 0.1021 and 0.0674, Mean Absolute Percentage Deviation values of 0.4945 and 0.3590, R2 scores of 0.9995 and 0.9998, and inference times of 0.0029 and 0.4299 s, respectively. The Explainable Artificial Intelligence analysis of the resulting models revealed some interesting insights into how the models make the predictions and what factors heavily contribute to the nanoparticle AVG_R, allowing chemists to optimize the synthesis for gold nanoparticles better. The key contributions of the research include the design and development of eight Machine Learning models using industry-standard frameworks, the training, tuning, and evaluation of these eight models using five different metrics, and further assessment of these trained models using Explainable Artificial Intelligence. The findings indicate a substantial potential for applying neural networks in the design phase of nanoparticle synthesis, which could lead to significant reductions in both the time and cost required for synthesizing Au nanoparticles for pharmaceutical applications.Publication Embargo ARCSECURE: Centralized Hub for Securing a Network of IoT Devices(Springer, Cham, 2021-07-06) Yapa Abeywardena, K; Abeykoon, A. M. I. S; Atapattu, A. M. S. P. B; Jayawardhane, H. N; Samarasekara, C. NAs far as it is considered, IoT has been a game changer in the advancement of technology. In the current context, the major issue that users face is the threat to their information stored in these devices. Modern day attackers are aware of vulnerabilities in existence in the current IoT environment. Therefore, securing information from being gone into the hands of unauthorized parties is of top priority. With the need of securing the information came the need of protecting the devices which the data is being stored. Small Office/Home Office (SOHO) environments working with IoT devices are particularly in need of such mechanism to protect the data and information that they hold in order to sustain their operations. Hence, in order come up with a well-rounded security mechanism from every possible aspect, this research proposes a plug and play device “ARCSECURE”.Publication Embargo SEAMS: A Symmetric Encryption Algorithm Modification System to Resist Power Based Side Channel Attacks(Springer, Cham, 2018-11-02) Pathirana, K. P. A. P; Lankarathne, L. R. M. O; Hangawaththa, N. H. A. D. A; Abeywardena, K. Y; Kuruwitaarachchi, NSide channel attacks which examine physical characteristics of a cryptographic algorithm, are getting much more popular in present days since it is easier to mount an attack in a short time with only a few hundred dollars’ worth of devices. Sensitive information of a cryptographic module can be easily identified by evaluating the side channel information, such as power consumption, heat and electromagnetic emissions that outputs from the cryptographic device. This creates a huge impact on the security of the cryptographic modules as it is an efficient technique to break cryptographic algorithms by analyzing the patterns of the side channel information without having any specialized knowledge in cryptography. The solution proposed in this paper is an algorithm modification system for symmetric algorithms in order to mitigate side channel attacks. This is achieved by injecting randomness to the algorithm following a comprehensive analysis of power fluctuations that outputs from a given algorithm. In the proposed solution, a hardware device tracks down the patterns in power consumption and analyze those meter readings by utilizing machine learning techniques. As a result of this analysis, it identifies the pattern generating source code positions. System will add random code fragments in to the identified positions in the algorithm without altering the output in order to resist side channel attacks.Publication Embargo Behavior & Bio metric based Masquerade Detection Mobile Application(Springer, Cham, 2019-07-29) Chandrasekara, P; Abeywardana, H; Rajapaksha, S; Sanjeevan, pMobile phone has become an important asset when it comes to information security since it has become a virtual safe. However, to protect the information inside the mobile, the manufacturers use the technologies as password protection, face recognition or fingerprint protection. Nevertheless, it is clear that these security methods can be bypassed. That is when the urge of a post-authentication is coming to the surface. In order to protect the phone from an unauthorized or illegitimate user this method is proposed as a solution. The aim of the proposed solution is to detect the illegitimate user by monitoring the behavior of the user by four main parameters. They are: 1) Keystroke dynamics with a customized keyboard; 2) location detection; 3) voice recognition; 4) Application usage. In the initial state machine learning is used to train this mobile application with the authentic user’s behavior and they are stored in a central database. After the initial training period the application is monitoring the usage and comparing it with the already saved data of the user. Another unique feature of this is the prevention mechanism it executes when an illegitimate user is detected. Furthermore, this application is proposed as an inbuilt application in order to avoid the deletion of app or uninstallation of the app by the intruder. With this Application which is introduced as “AuthDNA” will help you to protect the sensitive information of your mobile device in a case of theft and bypassing of initial authentication.Publication Embargo Code Vulnerability Identification and Code Improvement using Advanced Machine Learning(2019 1st International Conference on Advancements in Computing (ICAC), SLIIT, 2019-12-05) Ruggahakotuwa, L.; Rupasinghe, L.; Abeygunawardhana, P.Cyber-attacks are fairly mundane. The misconfigurations of the source code can result in security vulnerabilities that potentially encourage the attackers to exploit them and compromise the system. This paper aims to discover various mechanisms of automating the detection and correction of vulnerabilities in source code. Usage of static and dynamic analysis, various machine learning, deep learning, and neural network techniques will enhance the automation of detecting and correcting processes. This paper systematically presents the various methods and research efforts of detecting vulnerabilities in the source code, starting with what is a software vulnerability and what kind of exploitation, existing vulnerability detection methods, correction methods and efforts of best researches in the world relevant to the research area. A plugin will be developed which is capable of intelligently and efficiently detecting the vulnerable source code segment and correcting the source code accurately in the development stage.