arXiv subjects

Muhammad Shafique

Publications and source records attributed to Muhammad Shafique.

At least 109 records · Page 6Linked to original sources

arXiv2025

CapsBeam: Accelerating Capsule Network based Beamformer for Ultrasound Non-Steered Plane Wave Imaging on Field Programmable Gate Array

In recent years, there has been a growing trend in accelerating computationally complex non-real-time beamforming algorithms in ultrasound imaging using deep learning models. However, due to the large size and complexity these state-of-the-art deep learning techniques poses significant challenges when deploying on resource-constrained edge devices. In this work, we propose a novel capsule network based beamformer called CapsBeam, designed to operate on raw radio-frequency data and provide an envelope of beamformed data through non-steered plane wave insonification. Experiments on in-vivo data, CapsBeam reduced artifacts compared to the standard Delay-and-Sum (DAS) beamforming. For in-vitro data, CapsBeam demonstrated a 32.31% increase in contrast, along with gains of 16.54% and 6.7% in axial and lateral resolution compared to the DAS. Similarly, in-silico data showed a 26% enhancement in contrast, along with improvements of 13.6% and 21.5% in axial and lateral resolution, respectively, compared to the DAS. To reduce the parameter redundancy and enhance the computational efficiency, we pruned the model using our multi-layer LookAhead Kernel Pruning (LAKP-ML) methodology, achieving a compression ratio of 85% without affecting the image quality. Additionally, the hardware complexity of the proposed model is reduced by applying quantization, simplification of non-linear operations, and parallelizing operations. Finally, we proposed a specialized accelerator architecture for the pruned and optimized CapsBeam model, implemented on a Xilinx ZU7EV FPGA. The proposed accelerator achieved a throughput of 30 GOPS for the convolution operation and 17.4 GOPS for the dynamic routing operation.

cs.AR↗

arXiv2025

FL-QDSNNs: Federated Learning with Quantum Dynamic Spiking Neural Networks

We present Federated Learning-Quantum Dynamic Spiking Neural Networks (FL-QDSNNs), a privacy-preserving framework that maintains high predictive accuracy on non-IID client data. Its key innovation is a dynamic-threshold spiking mechanism that triggers quantum gates only when local data drift requires added expressiveness, limiting circuit depth and countering the accuracy loss typical of heterogeneous clients. Evaluated on different benchmark datasets, including Iris, where FL-QDSNNs reach 94% accuracy, the approach consistently surpasses state-of-the-art quantum-federated baselines; scaling analyses demonstrate that performance remains high as the federation expands to 25 clients, confirming both computational efficiency and collaboration robustness. By uniting adaptive quantum expressiveness with strict data locality, FL-QDSNNs enable regulation-compliant quantum learning for privacy-sensitive sectors and critical infrastructure.

quant-ph↗

arXiv2025

QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges

Recent advances in Large Language Models (LLMs) have demonstrated strong potential in code generation, yet their effectiveness in quantum computing remains underexplored. This paper benchmarks LLMs for PennyLane-based quantum code generation using real-world challenges from the Quantum Hackathon (QHack). We introduce QHackBench, a novel benchmark dataset derived from QHack competitions, and evaluate model performance under vanilla prompting and Retrieval-Augmented Generation (RAG). Our structured evaluation framework assesses functional correctness, syntactic validity, and execution success across varying challenge difficulties. Results indicate that RAG-enhanced models, supplemented with an augmented PennyLane dataset, approximately generate similar results as the standard prompting, particularly in complex quantum algorithms. Additionally, we introduce a multi-agent evaluation pipeline that iteratively refines incorrect solutions, further enhancing execution success rates. To foster further research, we commit to publicly releasing QHackBench, along with our evaluation framework and experimental results, enabling continued advancements in AI-assisted quantum programming.

cs.AI↗

arXiv2025

QUAV: Quantum-Assisted Path Planning and Optimization for UAV Navigation with Obstacle Avoidance

The growing demand for drone navigation in urban and restricted airspaces requires real-time path planning that is both safe and scalable. Classical methods often struggle with the computational load of high-dimensional optimization under dynamic constraints like obstacle avoidance and no-fly zones. This work introduces QUAV, a quantum-assisted UAV path planning framework based on the Quantum Approximate Optimization Algorithm (QAOA), to the best of our knowledge, this is one of the first applications of QAOA for drone trajectory optimization. QUAV models pathfinding as a quantum optimization problem, allowing efficient exploration of multiple paths while incorporating obstacle constraints and geospatial accuracy through UTM coordinate transformation. A theoretical analysis shows that QUAV achieves linear scaling in circuit depth relative to the number of edges, under fixed optimization settings. Extensive simulations and a real-hardware implementation on IBM's ibm_kyiv backend validate its performance and robustness under noise. Despite hardware constraints, results demonstrate that QUAV generates feasible, efficient trajectories, highlighting the promise of quantum approaches for future drone navigation systems.

quant-ph↗

arXiv2025

CircuitHunt: Automated Quantum Circuit Screening for Superior Credit-Card Fraud Detection

Designing effective quantum models for real-world tasks remains a key challenge within Quantum Machine Learning (QML), particularly in applications such as credit card fraud detection, where extreme class imbalance and evolving attack patterns demand both accuracy and adaptability. Most existing approaches rely on either manually designed or randomly initialized circuits, leading to high failure rates and limited scalability. In this work, we introduce CircuitHunt, a fully automated quantum circuit screening framework that streamlines the discovery of high-performing models. CircuitHunt filters circuits from the KetGPT dataset using qubit and parameter constraints, embeds each candidate into a standardized hybrid QNN, and performs rapid training with checkpointing based on macro-F1 scores to discard weak performers early. The top-ranked circuit is then fully trained, achieving 97% test accuracy and a high macro-F1 score on a challenging fraud detection benchmark. By combining budget-aware pruning, empirical evaluation, and end-to-end automation, CircuitHunt reduces architecture search time from days to hours while maintaining performance. It thus provides a scalable and task-driven tool for QML deployment in critical financial applications.

quant-ph↗

arXiv2025

Cutting is All You Need: Execution of Large-Scale Quantum Neural Networks on Limited-Qubit Devices

The rapid advancement in Quantum Computing, particularly through Noisy-Intermediate Scale Quantum (NISQ) devices, has spurred significant interest in Quantum Machine Learning (QML) applications. Despite their potential, fully-quantum algorithms remain impractical due to the limitations of current NISQ devices. Hybrid quantum-classical neural networks (HQNNs) have emerged as a viable alternative, leveraging both quantum and classical computations to enhance machine learning capabilities. However, the constrained resources of NISQ devices, particularly the limited number of qubits, pose significant challenges for executing large-scale quantum circuits. This work addresses these current challenges by proposing a novel and practical methodology for quantum circuit cutting of HQNNs, allowing large quantum circuits to be executed on limited-qubit NISQ devices. Our approach not only preserves the accuracy of the original circuits but also supports the training of quantum parameters across all subcircuits, which is crucial for the learning process in HQNNs. We propose a cutting methodology for HQNNs that employs a greedy algorithm for identifying efficient cutting points, and the implementation of trainable subcircuits, all designed to maximize the utility of NISQ devices in HQNNs. The findings suggest that quantum circuit cutting is a promising technique for advancing QML on current quantum hardware, since the cut circuit achieves comparable accuracy and much lower qubit requirements than the original circuit. The code is available at https://github.com/eBrain4Everyone/QNN-Cutting.

quant-ph↗

arXiv2025

TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks

Quantized Neural Networks (QNNs) are increasingly deployed in edge and resource-constrained environments due to their efficiency in computation and memory usage. While shown to distort the gradient landscape and weaken conventional pixel-level attacks, it provides limited robustness against patch-based adversarial attacks-localized, high-saliency perturbations that remain surprisingly transferable across bit-widths. Existing defenses either overfit to fixed quantization settings or fail to address this cross-bit generalization vulnerability. We introduce \textbf{TriQDef}, a tri-level quantization-aware defense framework designed to disrupt the transferability of patch-based adversarial attacks across QNNs. TriQDef consists of: (1) a Feature Disalignment Penalty (FDP) that enforces semantic inconsistency by penalizing perceptual similarity in intermediate representations; (2) a Gradient Perceptual Dissonance Penalty (GPDP) that explicitly misaligns input gradients across bit-widths by minimizing structural and directional agreement via Edge IoU and HOG Cosine metrics; and (3) a Joint Quantization-Aware Training Protocol that unifies these penalties within a shared-weight training scheme across multiple quantization levels. Extensive experiments on CIFAR-10 and ImageNet demonstrate that TriQDef reduces Attack Success Rates (ASR) by over 40\% on unseen patch and quantization combinations, while preserving high clean accuracy. Our findings underscore the importance of disrupting both semantic and perceptual gradient alignment to mitigate patch transferability in QNNs.

cs.CV↗

arXiv2025

MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel attacks, driving progress through adversarial iteration. This dynamic mirrors a strategic game of continual evolution. However, two major challenges hinder jailbreak development: the high cost of querying top-tier LLMs and the short lifespan of effective attacks due to frequent safety updates. These factors limit cost-efficiency and practical impact of research in jailbreak attacks. To address this, we propose MetaCipher, a low-cost, multi-agent jailbreak framework that generalizes across LLMs with varying safety measures. Using reinforcement learning, MetaCipher is modular and adaptive, supporting extensibility to future strategies. Within as few as 10 queries, MetaCipher achieves state-of-the-art attack success rates on recent malicious prompt benchmarks, outperforming prior jailbreak methods. We conduct a large-scale empirical evaluation across diverse victim models and benchmarks, demonstrating its robustness and adaptability. Warning: This paper contains model outputs that may be offensive or harmful, shown solely to demonstrate jailbreak efficacy.

cs.CR↗

arXiv2025

CognitiveArm: Enabling Real-Time EEG-Controlled Prosthetic Arm Using Embodied Machine Learning

Efficient control of prosthetic limbs via non-invasive brain-computer interfaces (BCIs) requires advanced EEG processing, including pre-filtering, feature extraction, and action prediction, performed in real time on edge AI hardware. Achieving this on resource-constrained devices presents challenges in balancing model complexity, computational efficiency, and latency. We present CognitiveArm, an EEG-driven, brain-controlled prosthetic system implemented on embedded AI hardware, achieving real-time operation without compromising accuracy. The system integrates BrainFlow, an open-source library for EEG data acquisition and streaming, with optimized deep learning (DL) models for precise brain signal classification. Using evolutionary search, we identify Pareto-optimal DL configurations through hyperparameter tuning, optimizer analysis, and window selection, analyzed individually and in ensemble configurations. We apply model compression techniques such as pruning and quantization to optimize models for embedded deployment, balancing efficiency and accuracy. We collected an EEG dataset and designed an annotation pipeline enabling precise labeling of brain signals corresponding to specific intended actions, forming the basis for training our optimized DL models. CognitiveArm also supports voice commands for seamless mode switching, enabling control of the prosthetic arm's 3 degrees of freedom (DoF). Running entirely on embedded hardware, it ensures low latency and real-time responsiveness. A full-scale prototype, interfaced with the OpenBCI UltraCortex Mark IV EEG headset, achieved up to 90% accuracy in classifying three core actions (left, right, idle). Voice integration enables multiplexed, variable movement for everyday tasks (e.g., handshake, cup picking), enhancing real-world performance and demonstrating CognitiveArm's potential for advanced prosthetic control.

cs.HC↗

arXiv2025

ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search

Hardware-aware Neural Architecture Search (NAS) is one of the most promising techniques for designing efficient Deep Neural Networks (DNNs) for resource-constrained devices. Surrogate models play a crucial role in hardware-aware NAS as they enable efficient prediction of performance characteristics (e.g., inference latency and energy consumption) of different candidate models on the target hardware device. In this paper, we focus on building hardware-aware latency prediction models. We study different types of surrogate models and highlight their strengths and weaknesses. We perform a systematic analysis to understand the impact of different factors that can influence the prediction accuracy of these models, aiming to assess the importance of each stage involved in the model designing process and identify methods and policies necessary for designing/training an effective estimation model, specifically for GPU-powered devices. Based on the insights gained from the analysis, we present a holistic framework that enables reliable dataset generation and efficient model generation, considering the overall costs of different stages of the model generation pipeline.

cs.LG↗

arXiv2025

Next-Generation Quantum Neural Networks: Enhancing Efficiency, Security, and Privacy

This paper provides an integrated perspective on addressing key challenges in developing reliable and secure Quantum Neural Networks (QNNs) in the Noisy Intermediate-Scale Quantum (NISQ) era. In this paper, we present an integrated framework that leverages and combines existing approaches to enhance QNN efficiency, security, and privacy. Specifically, established optimization strategies, including efficient parameter initialization, residual quantum circuit connections, and systematic quantum architecture exploration, are integrated to mitigate issues such as barren plateaus and error propagation. Moreover, the methodology incorporates current defensive mechanisms against adversarial attacks. Finally, Quantum Federated Learning (QFL) is adopted within this framework to facilitate privacy-preserving collaborative training across distributed quantum systems. Collectively, this synthesized approach seeks to enhance the robustness and real-world applicability of QNNs, laying the foundation for reliable quantum-enhanced machine learning applications in finance, healthcare, and cybersecurity.

quant-ph↗

arXiv2025

Quantum Portfolio Optimization with Expert Analysis Evaluation

Quantum algorithms have gained increasing attention for addressing complex combinatorial problems in finance, notably portfolio optimization. This study systematically benchmarks two prominent variational quantum approaches, Variational Quantum Eigensolver (VQE) and Quantum Approximate Optimization Algorithm (QAOA), under diverse experimental settings, including different asset universes, ansatz architectures, and circuit depths. Although both methods demonstrate effective cost function minimization, the resulting portfolios often violate essential financial criteria, such as adequate diversification and realistic risk exposure. To bridge the gap between computational optimization and practical viability, we introduce an Expert Analysis Evaluation framework in which financial professionals assess the economic soundness and the market feasibility of quantum-optimized portfolios. Our results highlight a critical disparity between algorithmic performance and financial applicability, emphasizing the necessity of incorporating expert judgment into quantum-assisted decision-making pipelines.

quant-ph↗

arXiv2025

KASPER: Kolmogorov Arnold Networks for Stock Prediction and Explainable Regimes

Forecasting in financial markets remains a significant challenge due to their nonlinear and regime-dependent dynamics. Traditional deep learning models, such as long short-term memory networks and multilayer perceptrons, often struggle to generalize across shifting market conditions, highlighting the need for a more adaptive and interpretable approach. To address this, we introduce Kolmogorov-Arnold networks for stock prediction and explainable regimes (KASPER), a novel framework that integrates regime detection, sparse spline-based function modeling, and symbolic rule extraction. The framework identifies hidden market conditions using a Gumbel-Softmax-based mechanism, enabling regime-specific forecasting. For each regime, it employs Kolmogorov-Arnold networks with sparse spline activations to capture intricate price behaviors while maintaining robustness. Interpretability is achieved through symbolic learning based on Monte Carlo Shapley values, which extracts human-readable rules tailored to each regime. Applied to real-world financial time series from Yahoo Finance, the model achieves an $R^2$ score of 0.89, a Sharpe Ratio of 12.02, and a mean squared error as low as 0.0001, outperforming existing methods. This research establishes a new direction for regime-aware, transparent, and robust forecasting in financial markets.

cs.LG↗

arXiv2025

PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation

The growing demand for robust quantum programming frameworks has unveiled a critical limitation: current large language model (LLM) based quantum code assistants heavily rely on remote APIs, introducing challenges related to privacy, latency, and excessive usage costs. Addressing this gap, we propose PennyCoder, a novel lightweight framework for quantum code generation, explicitly designed for local and embedded deployment to enable on-device quantum programming assistance without external API dependence. PennyCoder leverages a fine-tuned version of the LLaMA 3.1-8B model, adapted through parameter-efficient Low-Rank Adaptation (LoRA) techniques combined with domain-specific instruction tuning optimized for the specialized syntax and computational logic of quantum programming in PennyLane, including tasks in quantum machine learning and quantum reinforcement learning. Unlike prior work focused on cloud-based quantum code generation, our approach emphasizes device-native operability while maintaining high model efficacy. We rigorously evaluated PennyCoder over a comprehensive quantum programming dataset, achieving 44.3% accuracy with our fine-tuned model (compared to 33.7% for the base LLaMA 3.1-8B and 40.1% for the RAG-augmented baseline), demonstrating a significant improvement in functional correctness.

quant-ph↗

arXiv2025

Neuromorphic Computing for Embodied Intelligence in Autonomous Systems: Current Trends, Challenges, and Future Directions

The growing need for intelligent, adaptive, and energy-efficient autonomous systems across fields such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles is driving interest in neuromorphic computing. By drawing inspiration from biological neural systems, neuromorphic approaches offer promising pathways to enhance the perception, decision-making, and responsiveness of autonomous platforms. This paper surveys recent progress in neuromorphic algorithms, specialized hardware, and cross-layer optimization strategies, with a focus on their deployment in real-world autonomous scenarios. Special attention is given to event-based dynamic vision sensors and their role in enabling fast, efficient perception. The discussion highlights new methods that improve energy efficiency, robustness, adaptability, and reliability through the integration of spiking neural networks into autonomous system architectures. We integrate perspectives from machine learning, robotics, neuroscience, and neuromorphic engineering to offer a comprehensive view of the state of the field. Finally, emerging trends and open challenges are explored, particularly in the areas of real-time decision-making, continual learning, and the development of secure, resilient autonomous systems.

cs.LG↗

arXiv2025

ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-based Advanced Driver Assistance Systems

Advanced Driver Assistance Systems (ADAS) significantly enhance road safety by detecting potential collisions and alerting drivers. However, their reliance on expensive sensor technologies such as LiDAR and radar limits accessibility, particularly in low- and middle-income countries. Machine learning-based ADAS (ML-ADAS), leveraging deep neural networks (DNNs) with only standard camera input, offers a cost-effective alternative. Critical to ML-ADAS is the collision avoidance feature, which requires the ability to detect objects and estimate their distances accurately. This is achieved with specialized DNNs like YOLO, which provides real-time object detection, and a lightweight, detection-wise distance estimation approach that relies on key features extracted from the detections like bounding box dimensions and size. However, the robustness of these systems is undermined by security vulnerabilities in object detectors. In this paper, we introduce ShrinkBox, a novel backdoor attack targeting object detection in collision avoidance ML-ADAS. Unlike existing attacks that manipulate object class labels or presence, ShrinkBox subtly shrinks ground truth bounding boxes. This attack remains undetected in dataset inspections and standard benchmarks while severely disrupting downstream distance estimation. We demonstrate that ShrinkBox can be realized in the YOLOv9m object detector at an Attack Success Rate (ASR) of 96%, with only a 4% poisoning ratio in the training instances of the KITTI dataset. Furthermore, given the low error targets introduced in our relaxed poisoning strategy, we find that ShrinkBox increases the Mean Absolute Error (MAE) in downstream distance estimation by more than 3x on poisoned samples, potentially resulting in delays or prevention of collision warnings altogether.

cs.CV↗

arXiv2025

Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications

The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL) underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual Learning (NCL) appears as an emerging solution, by leveraging the principles of Spiking Neural Networks (SNNs) which enable efficient CL algorithms executed in dynamically-changed environments with resource-constrained computing systems. Motivated by the need for a holistic study of NCL, in this survey, we first provide a detailed background on CL, encompassing the desiderata, settings, metrics, scenario taxonomy, Online Continual Learning (OCL) paradigm, recent DNN-based methods to address catastrophic forgetting (CF). Then, we analyze these methods considering CL desiderata, computational and memory costs, as well as network complexity, hence emphasizing the need for energy-efficient CL. Afterward, we provide background of low-power neuromorphic systems including encoding techniques, neuronal dynamics, network architectures, learning rules, hardware processors, software and hardware frameworks, datasets, benchmarks, and evaluation metrics. Then, this survey comprehensively reviews and analyzes state-of-the-art in NCL. The key ideas, implementation frameworks, and performance assessments are also provided. This survey covers several hybrid approaches that combine supervised and unsupervised learning paradigms. It also covers optimization techniques including SNN operations reduction, weight quantization, and knowledge distillation. Then, this survey discusses the progress of real-world NCL applications. Finally, this paper provides a future perspective on the open research challenges for NCL, since the purpose of this study is to be useful for the wider neuromorphic AI research community and to inspire future research in bio-plausible OCL.

cs.NE↗

arXiv2025

QAS-QTNs: Curriculum Reinforcement Learning-Driven Quantum Architecture Search for Quantum Tensor Networks

Quantum Architecture Search (QAS) is an emerging field aimed at automating the design of quantum circuits for optimal performance. This paper introduces a novel QAS framework employing hybrid quantum reinforcement learning with quantum curriculum learning strategies, enabling learning agents to tackle increasingly complex quantum circuit design tasks. We benchmark four state-of-the-art classical reinforcement learning algorithms (A2C, PPO, DDQN, TD3) against their quantum-enhanced counterparts (QA2C, QPPO, QDDQN, QTD3) for optimizing variational quantum circuits (VQCs). Our approach progressively increases circuit depth and gate complexity during training, leveraging parameterized quantum circuits as function approximations. To improve learning efficiency and stability, all algorithms, both classical and quantum, are augmented with Prioritized Experience Replay (PER). Experimental results show that quantum-enhanced RL significantly outperforms classical methods. In a 2-qubit environment, PERQDDQN achieves a success probability of 0.46 with ~3,000 optimal successes, surpassing classical PERDDQN (0.42, ~2,400). In the more complex 3-qubit setting, PERQDDQN and PERQTD3 reach success probabilities of ~0.47, with optimal success counts of ~3,800 and ~3,600, respectively, outperforming their classical counterparts. Additionally, we apply our QAS-QTN approach to a classification problem, where the optimized quantum circuit achieves an accuracy of 90.33\%, outperforming quantum models consisting of random ansatz. This hybrid classical-quantum approach leads to faster convergence and more efficient quantum circuit designs, demonstrating its potential for advancing automated quantum architecture search.

quant-ph↗