arXiv subjects

Anuj Nepal

Publications and source records attributed to Anuj Nepal.

2 recordsLinked to original sources

arXiv2025

A Quantum-Secure and Blockchain-Integrated E-Voting Framework with Identity Validation

The rapid growth of quantum computing poses a threat to the cryptographic foundations of digital systems, requiring the development of secure and scalable electronic voting (evoting) frameworks. We introduce a post-quantum-secure evoting architecture that integrates Falcon lattice-based digital signatures, biometric authentication via MobileNetV3 and AdaFace, and a permissioned blockchain for tamper-proof vote storage. Voter registration involves capturing facial embeddings, which are digitally signed using Falcon and stored on-chain to ensure integrity and non-repudiation. During voting, real-time biometric verification is performed using anti-spoofing techniques and cosine-similarity matching. The system demonstrates low latency and robust spoof detection, monitored through Prometheus and Grafana for real-time auditing. The average classification error rates (ACER) are below 3.5% on the CelebA Spoof dataset and under 8.2% on the Wild Face Anti-Spoofing (WFAS) dataset. Blockchain anchoring incurs minimal gas overhead, approximately 3.3% for registration and 0.15% for voting, supporting system efficiency, auditability, and transparency. The experimental results confirm the system's scalability, efficiency, and resilience under concurrent loads. This approach offers a unified solution to address key challenges in voter authentication, data integrity, and quantum-resilient security for digital systems.

cs.CR↗

arXiv2025

A Novel Hierarchical Integration Method for Efficient Model Merging in Medical LLMs

Large Language Models (LLMs) face significant challenges in distributed healthcare, including consolidating specialized domain knowledge across institutions while maintaining privacy, reducing computational overhead, and preventing catastrophic forgetting during model updates.This paper presents a systematic evaluation of six parameter-space merging techniques applied to two architecturally compatible medical LLMs derived from the Mistral-7B base model. We introduce a novel hierarchical method that combines selective Optimal Transport (OT) alignment for attention layers with cosine similarity-weighted interpolation, designed to address permutation variance while minimizing computational overhead for edge deployment scenarios. Our study evaluates Task Arithmetic, Linear Averaging, DARE-TIES, DELLA, Breadcrumbs, and our Hierarchical approach across five medical benchmarks. Results demonstrate that architecturally compatible models benefit significantly from simple averaging methods, with Task Arithmetic achieving 45.80% accuracy on MedQA, outperforming complex pruning-based approaches. These findings offer critical insights for the deployment of distributed medical AI in resource-constrained IoT environments, where computational efficiency and model compatibility are paramount. Our work establishes that for architecturally compatible models, simple averaging provides a robust and computationally efficient baseline for knowledge consolidation, offering a pragmatic path forward for scalable medical AI systems.

cs.LG↗