Browsing by Author "Gamage, P"

Now showing 1 - 5 of 5

item: Conference-Full-text
Acoustic signature analysis for distinguishing human vs. synthetic voices in vishing attacks
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Gamage, P; Dissanayake, D; Kumarasinghe, N; Ganegoda, GU; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
Cybercrimes targeting mobile devices are on the rise, with vishing and smishing attacks being particularly prevalent. These attacks exploit social engineering techniques to manipulate individuals into divulging personal information or engaging in unintended actions. To counter this evolving threat landscape, this research proposes a pioneering methodology rooted in voice feature analysis. By distinguishing between human and robotic voices, this approach aims to discern legitimate calls from potential scams, thereby mitigating the associated financial losses and reputational damage. The research delves into the intricacies of voice feature analysis, leveraging natural language processing (NLP) and machine learning (ML) techniques to extract and analyze audio attributes such as pitch, volume, and temporal patterns. The ultimate objective is to create a binary classification model that accurately differentiates between human voice calls and robocalls, incorporating a comprehensive dataset comprising actual call recordings and synthesized scenarios. This research advances beyond conventional practices by championing a holistic analysis of both human and robocalls, contrary to the prevalent assumption of robocalls exclusively constituting scams. The application of various audio features, coupled with nuanced weightage allocation, enhances the model’s discernment capabilities. The resultant binary classifier is an exemplar of the innovative fusion of technology and human expertise. In conclusion, this research introduces a novel dimension to the combat against vishing and smishing attacks, with a robust voice feature analysis methodology capable of accurately identifying human and robotic voices. By effectively distinguishing legitimate calls from potential threats, this approach presents a promising avenue for safeguarding individuals and organizations against the far-reaching consequences of cybercrimes. The comprehensive analysis, validation, and insights presented in this paper contribute significantly to the field of cybersecurity and voicebased communication analysis.
item: Article-Full-text
Hot water washing of rice husk for ash removal: The effect of washing temperature, washing time and particle size
(Elsevier, 2020) Bandara, YW; Gamage, P; Gunarathne, DS
Rice husk is a carbon neutral and renewable source of energy and a biomaterial precursor, abundantly available at no cost. High ash content of rice husk is problematic for both applications and thus, reduction of ash constituents can be seen as a viable and sustainable solution. The effect of temperature, particle size and washing time on total ash removal percentage as well as elemental removal was evaluated. The ash leaching behavior was analyzed by fitting to a pseudo-second order kinetic model. 88–95% of K2O, 60–83% of P2O5, 38–54% of Fe2O3, 34–62% of Al2O3, 30–46% TiO2 and 19–24% of SiO2 has removed through water washing. According to the (K + Na)/(Ca + Mg) and (Si + K + P)/(Ca + Mg) molar ratios, ash melting tendency is expected to reduce significantly during combustion of washed rice husk. Increase of Ca and Mg in washed rice husk due to use of city water is beneficial for the ash chemistry. Washing temperature of 50 °C and 15 min of washing time with 1–1.4 mm particle size is recommended for washing pretreatment of rice husk.
item: Conference-Full-text
Leveraging artifact reputation analysis and contextual sentiment analysis for advanced detection of vishing and smishing attacks
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Dissanayake, D; Gamage, P; Kumarasinghe, N; Ganegoda, GU; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
The rise of advanced mobile technology has brought about the widespread presence of mobile devices in our society. These portable and versatile gadgets have become essential items for individuals due to their convenience and capabilities. As technology continues to play a pivotal role in modern life, an evergrowing number of people rely on mobile devices for almost all life activities including crucial financial activities and business routines. However, the increasing popularity of mobile devices has also exposed users to a heightened risk of falling victim to fraudulent schemes. Perpetrators have been exploiting mobile users by pretending to present authentic and legitimate requests and opportunities, leading to the divulgence of personal and sensitive information. These deceitful activities have seen a significant increase, affecting individuals of various ages, educational backgrounds, and levels of technological literacy. Additionally, malicious actors employ advanced methods to conceal their identities, making it challenging to prevent and counter these attacks. Two prevalent yet under-addressed issues in this context are vishing and smishing. This research study introduces a system designed to detect vishing and smishing attempts more accurately. The system analyzes the reputation of suspicious artifacts in messages and call conversations using third party threat intelligence services. Further, it employs natural language processing and machine learning techniques to examine the content of voice calls and SMS messages. It identifies suspicious elements such as keywords and phrases commonly used in phishing attacks, sensitive information as well as the context of the content.
item: Conference-Full-text
Seismic drift demand on multi-storey buildings in Sri Lanka due to long-distant earthquakes
(2013-11-26) Gamage, P; Venkatesan, S; Dissanayake, R
Intra-plate seismic activities in Northern Indian Ocean region below Sri Lanka, can be a possible threat of seismic hazard in terms of large magnitude long-distant earthquakes. Hypothesized seismic events with magnitudes 8, 7.5, 7 and 6, have been simulated based on this source by using the stochastic approach with estimated parameters for the Sri Lankan region. The crustal rock stratigraphy of the country consists mostly of crystalline rocks of Precambrian age, which governs the estimation of seismo-geological parameters were found to compare well with the well-known `hard rock’ conditions. Seismic response of structures from two major cities (Colombo and Hambantota) in the country was evaluated in terms of drift demands and base shears. The study includes both rock and soil sites. The soil amplification was carried out using the Extended Component Attenuation Model (ECAM) developed for typical intra-plate regions. Results show that, the base shear demands are far more significant than the drift demands for structures directly supported on rocks. Soft storey buildings directly founded on soil may experience higher drifts greater than allowable limits in some codes of practice. This suggests that important structures may need to be assessed using proper standards.
item: Conference-Full-text
Strengthening of damaged out of plane curved reinforced concrete beam using carbon fiber reinforced polymer
(IEEE, 2020-07) Kulendren, S; Fernando, C; Gamage, P; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
Curved major structures will get cracks and it will be costly and difficult to replace. So retrofitting technique in this paper will enable the engineers to retrofit these beams without replacing them. This experimental study aims at investigating the behaviour of damaged curved Reinforced Concrete (RC) beams strengthened with Carbon Fiber Reinforced Polymer (CFRP) sheets. Two sets of curved RC beam specimens, with 4000 mm radii were used. The beams were pre cracked and repaired by using epoxy grout prior to strengthening. The beams were retrofitted using an alternative bond arrangement of Near Surface Mounted (NSM) CFRP sheets. The specimens were tested under four-point bending test method. On average 51% increase in flexural gain was observed from retrofitted beams with respect to non-cracked control samples.