Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
5 results
Search Results
Item DANE: An inbuilt security extension(Institute of Electrical and Electronics Engineers Inc., 2016) Aishwarya, C.; Raghuram, M.A.; Hosmani, S.; Sannidhan, M.S.; Rajendran, B.; Chandrasekaran, K.; Bindhumadhava, B.S.Use of TSL and certificates in secure applications in the internet is very common today. Certificate authorities are playing the important role of trust anchors. But this means that third party certificate authorities have to be trusted by both domain owners and their clients. Compromises of certificate authorities will put many users under a huge risk. To solve this problem, the DANE protocol was proposed that is used on top of DNSSEC. It allows using the chain of trust in DNS for authenticating certificates and makes clients impose many constraints on the certificates they receive. We analyze the performance of the DANE protocol at the client side and also present a tool for deploying and administrating DANE with BIND servers in a local network. © 2015 IEEE.Item Corrosion Damage Identification and Lifetime Estimation of Ship Parts using Image Processing(Institute of Electrical and Electronics Engineers Inc., 2018) Naladala, I.; Raju, A.; Aishwarya, C.; Koolagudi, S.G.Corrosion is a process that leads to early failure of ship parts, high maintenance costs and a shortened service life of the ship, as a whole. Human visual inspection is currently the most widely used method to assess corrosion. In this paper, we propose the use of image processing to determine the extent of corrosion and estimate the time period within which the ship parts have to be replaced. In the case of availability of pre-corrosion images, the histograms of the pre-corrosion and post-corrosion images are compared and their similarity is quantified as the Sum of Squared Distances (SSD) value. Our method then produces a numerical output which signifies the level of corrosion. We then correlate extent of damage and ship part replacement period. In the absence of pre-corrosion images, we classify superpixels in the post-corrosion image as undamaged or damaged with an accuracy of 92 per cent, using Random Forest classifier. We have also evaluated the performance of corrosion prevention measures such as galvanization, painting, etc on different parts of the ship, for example, parts exposed to only air and parts exposed to both saline water and air. © 2018 IEEE.Item Ontology for Contextual Fake News Assessment Based on Text and Images(Institute of Electrical and Electronics Engineers Inc., 2024) Chandrasekaran, K.; Kandasamy, A.; Venkatesan, M.; Prabhavathy, P.; Gokuldhev, M.; Aishwarya, C.The spread of false news on social networks is a major challenge in the digital age across various sectors, encompassing technology, politics, public health, and finance. This paper introduces an ontology-based method that combines text and image analysis to evaluate the accuracy of news stories in the context of social media. We investigate the role of social engineering tactics in crafting and dispersing fake news and advocate for a comprehensive multi-contextual perspective that covers content, source, social media, psychological, and impact aspects. Using OWL (Web Ontology Language), we present an ontology framework for assessing fake news, providing a structured approach to analyze text, visuals, audio, audience behavior, source credibility, and news propagation patterns. This framework serves as a foundation for advanced detection systems, contributing to the fight against digital misinformation. © 2024 IEEE.Item Detecting Fake News: A Comparative Evaluation of Machine Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2024) Aishwarya, C.; Venkatesan, M.; Prabhavathy, P.; Shetty, A.S.Fake news is a significant and well-acknowledged problem in contemporary society due to its rapid spread via social media and various online networking platforms, thereby making it difficult to determine the validity of information. In this study, we examine literature for this issue, prevalent datasets like LIAR, Politifact, and COVID-19, as well as classical machine learning and deep learning models such as SVM, BiLSTM, and CNN- BiGRU for fake news detection, and analyze their effectiveness and scope of application for fake news detection. © 2024 IEEE.Item Grapevine SDLC Model for Real-Time Fake News Classification(Springer Science and Business Media Deutschland GmbH, 2025) Aishwarya, C.; Shekokar, T.P.; Naga Mukesh, K.; Venkatesan, M.; Prabhavathy, P.In an era of rapid information distribution, the presence of fake news presents enormous difficulties to society, influencing public opinion and decision-making on a global scale. To address this issue, a reliable and efficient system capable of detecting and classifying fake news in real time must be developed. This project proposes the design and implementation of a specialized Software Development Life Cycle (SDLC) model, called the Grapevine SDLC, specifically designed for developing a real-time fake news classifier using Large Language Models (LLMs) and Apache Kafka. The Grapevine SDLC takes a methodical, iterative approach, starting with a thorough requirements analysis that identifies both system capabilities and limitations. During the design and development phase, the system architecture is crafted with a focus on scalability and real-time processing, integrating LLMs for highly accurate content analysis and categorization. Kafka’s distributed messaging platform ensures seamless and efficient data streaming, enabling the system to handle large volumes of data in real time. Further, the model includes continuous monitoring and feedback loops to improve detection accuracy and adapt to evolving fake news patterns. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.