Searcharxiv⌕ Search

arXiv subjects

Shiva Raj Pokhrel

Publications and source records attributed to Shiva Raj Pokhrel.

At least 37 records · Page 2Linked to original sources
arXiv2025

QuantumShield: Multilayer Fortification for Quantum Federated Learning

In this paper, we propose a groundbreaking quantum-secure federated learning (QFL) framework designed to safeguard distributed learning systems against the emerging threat of quantum-enabled adversaries. As classical cryptographic methods become increasingly vulnerable to quantum attacks, our framework establishes a resilient security architecture that remains robust even in the presence of quantum-capable attackers. We integrate and rigorously evaluate advanced quantum and post-quantum protocols including Quantum Key Distribution (QKD), Quantum Teleportation, Key Encapsulation Mechanisms (KEM) and Post-Quantum Cryptography (PQC) to fortify the QFL process against both classical and quantum threats. These mechanisms are systematically analyzed and implemented to demonstrate their seamless interoperability within a secure and scalable QFL ecosystem. Through comprehensive theoretical modeling and experimental validation, this work provides a detailed security and performance assessment of the proposed framework. Our findings lay a strong foundation for next-generation federated learning systems that are inherently secure in the quantum era.

cs.CR↗
arXiv2025

Adapting Quantum Machine Learning for Energy Dissociation of Bonds

Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansatz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near chemical accuracy.

quant-ph↗
arXiv2025

Digital Privacy Under Attack: Challenges and Enablers

We present a comprehensive analysis of privacy attacks and countermeasures in data-driven systems. We systematically categorize attacks targeting three domains: anonymous data (linkage and structural attacks), statistical aggregates (reconstruction and differential attacks), and privacy-preserving models (extraction, reconstruction, membership inference, and inversion attacks). For each category, we analyze attack methodologies, adversary capabilities, and vulnerability mechanisms. We further evaluate countermeasures including perturbation techniques, randomization methods, query auditing, and model-level defenses, examining their effectiveness and inherent privacy-utility tradeoffs. Our analysis reveals that while differential privacy offers strong theoretical guarantees, it faces implementation challenges and potential vulnerabilities to emerging attacks. We identify critical research directions and provide researchers and practitioners with a structured framework for understanding privacy resilience in increasingly complex data ecosystems.

cs.CR↗
arXiv2025

sat-QFL: Secure Quantum Federated Learning for Low Orbit Satellites

Low Earth orbit (LEO) constellations violate core assumptions of standard (quantum) federated learning (FL): client-server connectivity is intermittent, participation is time varying, and latency budgets are strict. We present sat-QFL, a hierarchical, access aware quantum federated learning (QFL) framework that partitions satellites into primary (ground connected) and secondary as inter-satellite links (ISL-only) roles, and schedules sequential, simultaneous, or asynchronous edge training aligned with visibility windows. For quantum-resilient confidentiality and integrity, sat-QFL integrates quantum key distribution (QKD) based key establishment with authenticated encryption for model exchange; we also assess teleportation as a feasibility primitive for quantum state transfer. Using derived constellation traces and QFL workloads (Qiskit), we show that sat-QFL sustains robust aggregation under varying participation and reduces communication bottlenecks with modest security overhead. Our implementation and results are available at https://github.com/s222416822/satQFL.

cs.DC↗
arXiv2025

orb-QFL: Orbital Quantum Federated Learning

Recent breakthroughs in quantum computing present transformative opportunities for advancing Federated Learning (FL), particularly in non-terrestrial environments characterized by stringent communication and coordination constraints. In this study, we propose orbital QFL, termed orb-QFL, a novel quantum-assisted Federated Learning framework tailored for Low Earth Orbit (LEO) satellite constellations. Distinct from conventional FL paradigms, termed orb-QFL operates without centralized servers or global aggregation mechanisms (e.g., FedAvg), instead leveraging quantum entanglement and local quantum processing to facilitate decentralized, inter-satellite collaboration. This design inherently addresses the challenges of orbital dynamics, such as intermittent connectivity, high propagation delays, and coverage variability. The framework enables continuous model refinement through direct quantum-based synchronization between neighboring satellites, thereby enhancing resilience and preserving data locality. To validate our approach, we integrate the Qiskit quantum machine learning toolkit with Poliastro-based orbital simulations and conduct experiments using Statlog dataset.

cs.DC↗
arXiv2025

Understanding BBRv3 Performance in AQM-Enabled WiFi Networks

We present a modular experimental testbed and lightweight visualization tool for evaluating TCP congestion control performance in wireless networks. We compare Google's latest Bottleneck Bandwidth and Round-trip time version 3 (BBRv3) algorithm with loss-based CUBIC under varying Active Queue Management (AQM) schemes, namely PFIFO, FQ-CoDel, and CAKE, on a Wi-Fi link using a commercial MikroTik router. Our real-time dashboard visualizes metrics such as throughput, latency, and fairness across competing flows. Results show that BBRv3 significantly improves fairness and convergence under AQM, especially with FQ-CoDel. Our visualization tool and modular testbed provide a practical foundation for evaluating next-generation TCP variants in real-world AQM-enabled home wireless networks.

cs.NI↗
arXiv2025

Distilling Large Language Models for Network Active Queue Management

The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high engineering effort. We propose AQM-LLM, distilling Large Language Models (LLMs) with few-shot learning, contextual understanding, and pattern recognition to improve Active Queue Management (AQM) [RFC 9330] with minimal manual effort. We consider a specific case where AQM is Low Latency, Low Loss, and Scalable Throughput (L4S) and our design of AQM-LLM builds on speculative decoding and reinforcement-based distilling of LLM by tackling congestion prevention in the L4S architecture using Explicit Congestion Notification (ECN) [RFC 9331] and periodic packet dropping. We develop a new open-source experimental platform by executing L4S-AQM on FreeBSD-14, providing interoperable modules to support LLM integration and facilitate IETF recognition through wider testing. Our extensive evaluations show L4S-LLM enhances queue management, prevents congestion, reduces latency, and boosts network performance, showcasing LLMs' adaptability and efficiency in uplifting AQM systems.

cs.NI↗
arXiv2025

Intelligent Spectrum Management in Satellite Communications

Satellite Communication (SatCom) networks represent a fundamental pillar in modern global connectivity, facilitating reliable service and extensive coverage across a plethora of applications. The expanding demand for high-bandwidth services and the proliferation of mega satellite constellations highlight the limitations of traditional exclusive satellite spectrum allocation approaches. Cognitive Radio (CR) leading to Cognitive Satellite (CogSat) networks through Dynamic Spectrum Management (DSM), which enables the dynamic adaptability of radio equipment to environmental conditions for optimal performance, presents a promising solution for the emerging spectrum scarcity. In this survey, we explore the adaptation of intelligent DSM methodologies to SatCom, leveraging satellite network integrations. We discuss contributions and hurdles in regulations and standardizations in realizing intelligent DSM in SatCom, and deep dive into DSM techniques, which enable CogSat networks. Furthermore, we extensively evaluate and categorize state-of-the-art Artificial Intelligence (AI)/Machine Learning (ML) methods leveraged for DSM while exploring operational resilience and robustness of such integrations. In addition, performance evaluation metrics critical for adaptive resource management and system optimization in CogSat networks are thoroughly investigated. This survey also identifies open challenges and outlines future research directions in regulatory frameworks, network architectures, and intelligent spectrum management, paving the way for sustainable and scalable SatCom networks for enhanced global connectivity.

cs.NI↗
arXiv2025

New Insights on Unfolding and Fine-tuning Quantum Federated Learning

Client heterogeneity poses significant challenges to the performance of Quantum Federated Learning (QFL). To overcome these limitations, we propose a new approach leveraging deep unfolding, which enables clients to autonomously optimize hyperparameters, such as learning rates and regularization factors, based on their specific training behavior. This dynamic adaptation mitigates overfitting and ensures robust optimization in highly heterogeneous environments where standard aggregation methods often fail. Our framework achieves approximately 90% accuracy, significantly outperforming traditional methods, which typically yield around 55% accuracy, as demonstrated through real-time training on IBM quantum hardware and Qiskit Aer simulators. By developing self adaptive fine tuning, the proposed method proves particularly effective in critical applications such as gene expression analysis and cancer detection, enhancing diagnostic precision and predictive modeling within quantum systems. Our results are attributed to convergence-aware, learnable optimization steps intrinsic to the deep unfolded framework, which maintains the generalization. Hence, this study addresses the core limitations of conventional QFL, streamlining its applicability to any complex challenges such as healthcare and genomic research.

cs.LG↗
arXiv2025

Communication Efficient Adaptive Model-Driven Quantum Federated Learning

Training with huge datasets and a large number of participating devices leads to bottlenecks in federated learning (FL). Furthermore, the challenges of heterogeneity between multiple FL clients affect the overall performance of the system. In a quantum federated learning (QFL) context, we address these three main challenges: i) training bottlenecks from massive datasets, ii) the involvement of a substantial number of devices, and iii) non-IID data distributions. We introduce a model-driven quantum federated learning algorithm (mdQFL) to tackle these challenges. Our proposed approach is efficient and adaptable to various factors, including different numbers of devices. To the best of our knowledge, it is the first to explore training and update personalization, as well as test generalization within a QFL setting, which can be applied to other FL scenarios. We evaluated the efficiency of the proposed mdQFL framework through extensive experiments under diverse non-IID data heterogeneity conditions using various datasets within the Qiskit environment. Our results demonstrate a nearly 50% decrease in total communication costs while maintaining or, in some cases, exceeding the accuracy of the final model and consistently improving local model training compared to the standard QFL baseline. Moreover, our experimental evaluation thoroughly explores the QFL and mdQFL algorithms, along with several influencing factors. In addition, we present a theoretical analysis to clarify the complexities of the proposed algorithm. The experimental code is available at 1.

cs.LG↗
arXiv2025

LLM-QFL: Distilling Large Language Model for Quantum Federated Learning

Inspired by the power of large language models (LLMs), our research adapts them to quantum federated learning (QFL) to boost efficiency and performance. We propose a federated fine-tuning method that distills an LLM within QFL, allowing each client to locally adapt the model to its own data while preserving privacy and reducing unnecessary global updates. The fine-tuned LLM also acts as a reinforcement agent, optimizing QFL by adjusting optimizer steps, cutting down communication rounds, and intelligently selecting clients. Experiments show significant efficiency gains. We pioneer a synergy between LLM and QFL, offering: i) practical efficiency: Reduced communication costs and faster convergence. ii) theoretical rigor: Provable guarantees for adaptive federated optimization. iii) scalability: PEFT methods (LoRA, QLoRA) enable deployment on resource-constrained quantum devices. Code implementation is available here 1.

cs.LG↗
arXiv2025

Towards A Hybrid Quantum Differential Privacy

Quantum computing offers unparalleled processing power but raises significant data privacy challenges. Quantum Differential Privacy (QDP) leverages inherent quantum noise to safeguard privacy, surpassing traditional DP. This paper develops comprehensive noise profiles, identifies noise types beneficial for QDP, and highlights teh need for practical implementations beyond theoretical models. Existing QDP mechanisms, limited to single noise sources, fail to reflect teh multi-source noise reality of quantum systems. We propose a resilient hybrid QDP mechanism utilizing channel and measurement noise, optimizing privacy budgets to balance privacy and utility. Additionally, we introduce Lifted Quantum Differential Privacy, offering enhanced randomness for improved privacy audits and quantum algorithm evaluation.

quant-ph↗
arXiv2025

Modeling Quantum Machine Learning for Genomic Data Analysis

Quantum Machine Learning (QML) continues to evolve, unlocking new opportunities for diverse applications. In this study, we investigate and evaluate the applicability of QML models for binary classification of genome sequence data by employing various feature mapping techniques. We present an open-source, independent Qiskit-based implementation to conduct experiments on a benchmark genomic dataset. Our simulations reveal that the interplay between feature mapping techniques and QML algorithms significantly influences performance. Notably, the Pegasos Quantum Support Vector Classifier (Pegasos-QSVC) exhibits high sensitivity, particularly excelling in recall metrics, while Quantum Neural Networks (QNN) achieve the highest training accuracy across all feature maps. However, the pronounced variability in classifier performance, dependent on feature mapping, highlights the risk of overfitting to localized output distributions in certain scenarios. This work underscores the transformative potential of QML for genomic data classification while emphasizing the need for continued advancements to enhance the robustness and accuracy of these methodologies.

cs.LG↗
arXiv2025

Modeling Feature Maps for Quantum Machine Learning

Quantum Machine Learning (QML) offers significant potential for complex tasks like genome sequence classification, but quantum noise on Noisy Intermediate-Scale Quantum (NISQ) devices poses practical challenges. This study systematically evaluates how various quantum noise models including dephasing, amplitude damping, depolarizing, thermal noise, bit-flip, and phase-flip affect key QML algorithms (QSVC, Peg-QSVC, QNN, VQC) and feature mapping techniques (ZFeatureMap, ZZFeatureMap, and PauliFeatureMap). Results indicate that QSVC is notably robust under noise, whereas Peg-QSVC and QNN are more sensitive, particularly to depolarizing and amplitude-damping noise. The PauliFeatureMap is especially vulnerable, highlighting difficulties in maintaining accurate classification under noisy conditions. These findings underscore the critical importance of feature map selection and noise mitigation strategies in optimizing QML for genomic classification, with promising implications for personalized medicine.

cs.LG↗
arXiv2024

Adapting Large Language Models for Improving TCP Fairness over WiFi

The new transmission control protocol (TCP) relies on Deep Learning (DL) for prediction and optimization, but requires significant manual effort to design deep neural networks (DNNs) and struggles with generalization in dynamic environments. Inspired by the success of large language models (LLMs), this study proposes TCP-LLM, a novel framework leveraging LLMs for TCP applications. TCP-LLM utilizes pre-trained knowledge to reduce engineering effort, enhance generalization, and deliver superior performance across diverse TCP tasks. Applied to reducing flow unfairness, adapting congestion control, and preventing starvation, TCP-LLM demonstrates significant improvements over TCP with minimal fine-tuning.

cs.NI↗
arXiv2024

Robust Zero Trust Architecture: Joint Blockchain based Federated learning and Anomaly Detection based Framework

This paper introduces a robust zero-trust architecture (ZTA) tailored for the decentralized system that empowers efficient remote work and collaboration within IoT networks. Using blockchain-based federated learning principles, our proposed framework includes a robust aggregation mechanism designed to counteract malicious updates from compromised clients, enhancing the security of the global learning process. Moreover, secure and reliable trust computation is essential for remote work and collaboration. The robust ZTA framework integrates anomaly detection and trust computation, ensuring secure and reliable device collaboration in a decentralized fashion. We introduce an adaptive algorithm that dynamically adjusts to varying user contexts, using unsupervised clustering to detect novel anomalies, like zero-day attacks. To ensure a reliable and scalable trust computation, we develop an algorithm that dynamically adapts to varying user contexts by employing incremental anomaly detection and clustering techniques to identify and share local and global anomalies between nodes. Future directions include scalability improvements, Dirichlet process for advanced anomaly detection, privacy-preserving techniques, and the integration of post-quantum cryptographic methods to safeguard against emerging quantum threats.

cs.CR↗
arXiv2024

Analysis, Modeling and Design of Personalized Digital Learning Environment

This research analyzes, models and develops a novel Digital Learning Environment (DLE) fortified by the innovative Private Learning Intelligence (PLI) framework. The proposed PLI framework leverages federated machine learning (FL) techniques to autonomously construct and continuously refine personalized learning models for individual learners, ensuring robust privacy protection. Our approach is pivotal in advancing DLE capabilities, empowering learners to actively participate in personalized real-time learning experiences. The integration of PLI within a DLE also streamlines instructional design and development demands for personalized teaching/learning. We seek ways to establish a foundation for the seamless integration of FL into learning systems, offering a transformative approach to personalized learning in digital environments. Our implementation details and code are made public.

cs.HC↗