Authors - Darshan L.M, Nagasundara K.B Abstract - Nowadays, most of the people alters/or conceals their true facial appearance intentionally and/or unintentionally by wearing various disguise accessories such as sunglasses, artificial beard and moustache, face make-up, and many more fancy items. Since, these accessories obscures the prominent facial features, the traditional face recognition systems have not shown a notable recognition performance and thus its performance is challengeable in the various applications fields such as immigration and border control, national security, surveillance, and many more. In literature, IIIT-DDFD, IMFDB, and FDB are disguise datasets are available for Indian ethnicity. Our analysis indicates that, these datasets are not sufficient with enough facial samples to meet the current trends. Therefore, we have introduced an Indian celebrity disguise face dataset (ICDFD), which includes the samples with wide range of complex disguise variations combined with pose, illumination, and expression. Initially, we analyze the performance of these datasets using holistic approaches and followed by deep learning models. From the experimental analysis, it reveals that the deep learning models have shown an optimal performance over holistic approaches. It is observed that, the disguised faces are continue to pose wide open challenges for the researchers in the area of computer vision.
Authors - Harini S, Shamila Ebenezer A Abstract - The document introduces a protected blockchain application for patient care that improves system visibility and operational speed. The application allows patients to book appointments which hospital administrators check before authorization. Following permission by administrators, patients may evaluate their appointment schedule and doctors analyze medical records for medical assessments. Specialist approval must authorize the download of prescription reports. Through blockchain technology physicians can perform decentralized transactions as well as track assets and exchange secure data which leads to lower operational costs and better trust and platform collaboration between patients and specialists and administrators.
Authors - Vishwesh Kumbhre, M. L. Dhore, Pradhynan Lohar, Ajinkya Lende, Om Popade, Shivkumar Padalwar Abstract - Augmented Reality has contributed in many important fields like Education and other fields like Medical and Military, which needs 100% accuracy and focus while performing certain operations. These tasks can be perfected if you have a thorough practice of every situation and gain knowledge about everything being used in that instance. This requirement is fulfilled by Augmented Reality where it creates virtual objects on a real-world background which gives us a real time experience, as if we are actually performing these tasks using solid objects. And the responses are as legit as they would be, in real experiments. Using these features, we can make different software which guides the students and cadets in real life situations.
Authors - Anjali Mahavar, Atul Patel, Ashish Patel Abstract - When given to the human body, different substances and products might present varying health hazards. Concerns regarding toxicity have caused fewer new medicines to access the market throughout the years via the conventional drug development path. The choice of lead compounds and ADMET research depends much on the use of in silico toxicity prediction techniques as ethics, time, money, and other resources often limit in vitro and in vivo approaches. In this regard, we propose a variety of toxicity tools that use structural and physicochemical- based characteristics in the form of molecular descriptors and fingerprints to assess the carcinogenicity of five distinct imidazo[1,2,a]pyridine ligands, including Protox-3, VenomPred, PkCSm, etc. According to the results of the in silico toxicity tool, ligand-1 (IP-1) has a low likelihood of carcinogenicity (0.56%) and excellent accuracy (67.38%) when compared to other ligands. As a consequence, it can be the first choice for medication development in the treatment of cancer.
Thursday August 27, 2026 12:30pm - 2:30pm IST Virtual Room AGOA, India
Authors - Atharv Khunte, Vishakha Dhotare, Divya Pawar, Nikita Dandgavhal, V.M Kokane Abstract - For increasing cyberattacks, web applications require robust and scalable security mechanisms. We suggest a centralized firewall structure that effectively detects and blocks attacks on multiple hosts simultaneously. The system is a command center that collects information about attacks from clients not yet attacked. Information collected is transmitted to the afflicted client only after receiving all necessary details. The system works by detecting and neutralizing various forms of cyberattacks such as SQL injection (SQLi), cross-site scripting (XSS), and distributed denial-of-service (DDoS) attacks. As soon as malicious activity is detected, the system will automatically block the attacking IP address, preventing further intrusion. This process enhances real-time protection, limiting the likelihood of repeated cyberattacks on interconnected web applications. By employing a single defense method, this centralized firewall maximizes threat intelligence sharing, rendering all the connected clients secure. Unlike standalone firewalls in the past, this approach consolidates security policies and enhances cybersecurity resilience on various platforms. Further, this system not only secures web applications against emerging threats but also ensures that organizations meet cybersecurity compliance requirements by hosting a neat and responsive security mechanism. The centralized structure of the fire-wall provides early attack detection, largely reducing downtime, data loss, and monetary loss.
Thursday August 27, 2026 12:30pm - 2:30pm IST Virtual Room AGOA, India
Authors - Prajakta Prasad Kohale, Michael Savariapitchai Abstract - Communication is fundamental for quality healthcare. It is the bridge between the patients and the provider. The basis of any group teamwork and an important factor in an efficient healthcare system is communication. The objective of this paper is to trace the history of communication’s evolution from basic, traditional models to the complex systems that are present in modern-day healthcare. Effective communication helps in establishing trust and confidence which motivates both the patients and the care teams to work together and take accountability for their health. The most favorable health outcomes are shown in patients who feel most sincerely cared for.
Authors - A.Punidha, E.Arul, E.Yuvarani, S.Rajasakaran Abstract - Device drivers are a critical component of modern computing but are increasingly targeted by attackers to gain unauthorized access, execute malicious code, or escalate privileges. Traditional malware detection techniques, such as signature-based and heuristic methods, struggle against advanced threats that employ evasion tactics. To address this, we propose a Graph Neural Network (GNN)-based framework that leverages feature engineering and graph-based learning to detect malicious drivers with high accuracy.By modeling system execution as a graph, our approach captures complex dependencies between API calls, memory accesses, and kernel interactions. We employ Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) to analyze these relationships, enabling detection of even stealthy and obfuscated malware.Experiments on Windows, Linux, and Android driver datasets demonstrate that our model achieves a 95.8% accuracy, outperforming Random Forest, XGBoost, LSTM, and CNNs. The model is also robust against adversarial evasion techniques, making it a scalable and effective solution for endpoint security, malware sandboxing, and kernel protection.
Thursday August 27, 2026 12:30pm - 2:30pm IST Virtual Room AGOA, India
Authors - R Saiprithvi, Sindhu Chandra Sekharan, Summia Parveen, Ajanthaa Lakkshmanan, Jesline D Abstract - Diseases of lungs like asthma, Chronic obstructive pulmonary disease, lung cancer are among the leading causes of death across the world. Ensuring better outcomes for patients with any medical condition requires an early diagnosis which is, unfortunately, technologically impossible in many regions. This work presents a multimodal Conversational Artificial Intelligence approach based on X-ray imaging, respiratory sound processing, and conversational interfaces that can help with the early and easy diagnosis of lung health. A Convolution Neural Network Processes X-ray images and reliably captures abnormalities. A Random Forest classifier examines MFCC features of lung sounds to confirm presence of asthma, bronchitis, and other diseases. The last method involves using a conversational AI chatbot that makes the collection of symptoms more convenient and provides the user with further information. with the capture of volumetric imaging, sound, and text, healthcare accessibility, efficiency, and diagnostics can be achieved using Artificial intelligence in imaging technology. Lung health is of primary importance, but millions of people worldwide live with easily preventable respiratory disease. EWHO alone estimates that more than 300 million people around the globe suffer from chronic lung disorders, including asthma, Lung
Authors - Job Joseph, Shivaprakash S, Rahul, Rojalin Patri Abstract - This research investigates the impact of financial influencers (finfluencers) on investment decisions of students using trust, perceived risk, and ethical concerns. Correlation and regression analysis reveal strong inter-linkages among them. The implications are drawn noting students' increasing utilization of social media as a source of personal finance information and both its benefits and risks. This work informs financial literacy scholarship and provides recommendations for policy change to contain the influence of finfluencers. Additionally, findings from current research show that finfluencers are not only educators but also business entities that act with self-interest, influencing market behaviour and investment decision-making among retail investors.
Authors - Dheeraj Hegde, Aishwarya Kalatippi, Prajwal Shiggavi, Satish Chikkamath, Nirmala S.R Abstract - This study presents a novel approach to image representation, utilizing wavelet transforms to compress image information into a compact latent space. Wavelet transforms offer a multi-resolution analysis, decomposing images into different frequency components at different resolution scales, emphasizing the spatial and frequency attributes. By leveraging the hierarchical structure of wavelet coefficients, we construct a latent space representation preserving essential features while reducing dimensionality. Experimental evaluations on benchmark datasets demonstrate competitive performance in tasks such as compression and classification compared to traditional deep learning approaches. Waveletbased representation offers promise for addressing challenges in highdimensional data while retaining crucial image information for diverse processing tasks.
