Guardian-Based Anonymous Password Management with Privacy Preservation Using Threshold Cryptography Harivignesh K.S., Venkatesan R., Selvarathi M., Jasmine David D. Journal of Trends in Computer Science and Smart Technology, 2026 Most password managers are designed as a compromise between providing a secure way to handle difficult login credentials and creating a system that keeps user information private. Most password managers store users’ sensitive information in a central location, leaving users vulnerable to hacking attacks. The proposed work creates a better way to manage passwords and provide more protection to users based on their private information through a new concept called Guardian-Anonymous Password Management (GAPM). The idea is to create a unique architecture that stores passwords in decentralized locations using guardian anonymity, creating a hybrid architecture of secret sharing with post-quantum encrypted wraps. Accordingly, GAPM separates the act of recovering user passwords from a person, using a set of anonymous guardians who securely recover users’ passwords without putting any of them at risk of being hacked or located through social engineering techniques like phishing. This is achieved by using a Shamir-style secret sharing scheme combined with verifiably reassured commitments, where none of the guardians know each other, and they are required to reach a certain threshold of agreement to combine their shares into an easily accessible password recovery key. The GAPM system supports multiple guardian sets, allowing participants to be added or removed, and there is no need to reissue all the shares each time users make a change. The user can also change the recovery threshold in real-time. Finally, the shares are further secured through the use of a post-quantum Key Encapsulation Mechanism (KEM) to ensure that, no matter what kind of attack (classical or quantum), the password recovery process will remain strong and secure.
An Elegant Privacy Preservation and De-Duplication Model With Elliptic Revocation Cryptography (PPD-ERC) Framework for Cloud Security L. Selvam, R. Gomathi, R. Venkatesan Transactions on Emerging Telecommunications Technologies, 2026 Due to the rapid advancement of communication technology, ensuring cloud data privacy and security is now regarded as one of the most important and difficult tasks. The traditional works are highly concentrated on creating cryptographic models for enhancing cloud system security. However, it encountered issues and problems because of the following factors: increased system overhead, time and storage requirements, complex mathematical operations, and ineffective data handling. In order to guarantee the security, privacy, and access control of cloud data sharing, the proposed work aims to develop a novel framework known as the Privacy Preservation and De‐duplication Model with Elliptic Revocation Cryptography (PPD‐ERC). This framework includes the entities of Cloud User (CU) (i.e., owner or receiver), Cloud Encryption Server (CES), sub‐CES, and Trusted Authority. Here, the lightweight ERC methodology encrypts user data using the private and public key pair. Then, the convergent keys are distributed to the blockchain, and the CU uses the Share algorithm for splitting the convergent keys. The CES validates the user authenticity based on the access controlling mechanism, which allows only the authorized users to obtain the data from server. Moreover, data de‐duplication is performed to avoid redundant encrypted data storage in the cloud system, and it increases the processing speed, minimizes the storage space, and optimizes the key generation process. During performance analysis, various evaluation metrics have been used to validate and compare the results of the proposed PPD‐ERC mechanism.
Temporal CAT-Based Data Fusion for IoMT System R. Venkatesan, A. Saravanan, A. Sathya Proceedings of the 12th International Conference on Biosignals Images and Instrumentation Icbsii 2026, 2026
MindMate: AI-Powered Multilingual Mental Health Chatbot with Personalized Voice and Text Support with Rasa and Streamlit Dharshini S, Samson Arun Raj A, Venkatesan R Proceedings of the International Conference on Intelligent Computing and Control Systems Iciccs 2025, 2025 An AI motivated mental health chat bot which can enable personalized support through voice as well as text based interaction, it’s dubbed as MindMate. Using the Rasa framework for natural language understanding (NLU) and dialogue management, along with Streamlit to make the interface user friendly and breathable for people, it makes an empathetic environment to allow people to express themselves and get responses from it. It is a multilingual chatbot, so it can be used by a lot of people with different languages. MindMate approaches users with a personalized approach to learn from user interactions to provide personalized responses, suggestions and resources that respond to the individual needs and preferences. This unique system not only makes it easy to share how you feel, but also gives you useful resources for dealing with whatever problem or issue you may be facing, helping to solve those problems. MindMate hopes to change the game of mental health support, incorporating advanced AI technology into an intuitive interface meant to ensure that mental well-being is readily available and effective for people seeking assistance with how to manage that aspect of their life.
Sarcasm Aware Sentiment Analysis with BERT Transformer Models Samuel M, K Ramalakshmi, R Venkatesan, Agnes Chella Wanika R Proceedings of the 4th International Conference on Intelligent Computing Information and Control Systems Icoiics 2025, 2025
ML-Based Medical diagnosis for skin disease Gokul B, R Venkatesan, Swetha Shekarappa G, Senbagavalli M Icrteect 2025 2nd International Conference on Recent Trends in Electrical Electronics and Computing Technologies, 2025
Demystifying the Industry 5.0 Version Venkatesan Ramachandran, Feroze Ahamed Zahir Ahamed, Thanga Helina Stalin, Shirley Chellathurai Pon Anna Bai Edge AI for Industry 5 0 and Healthcare 5 0 Applications, 2025
A Hybrid Stacked Ensemble Approach for Stock Market Volatility Prediction David Rosario Selvaraj, K Ramalakshmi, D. Ponmary Pushpa Latha, Agnes Chella Wanika R, R Venkatesan Proceedings of 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things Icoici 2025, 2025