arXiv subjects

Muhammad Shafique

Publications and source records attributed to Muhammad Shafique.

At least 73 records · Page 4Linked to original sources

arXiv2026

GAT-QNN: Genetic Algorithm-Based Training of Hybrid Quantum Neural Networks

Hybrid Quantum Neural Networks (HQNNs) combine classical learning with parameterized quantum circuits, but their practical performance is often limited by (i) the noise of Noisy Intermediate-Scale Quantum (NISQ) devices and (ii) the large, discrete design space of quantum circuit architectures. Moreover, HQNNs are commonly trained using a fixed circuit and a single backend, even though deployment frequently targets heterogeneous backends where compilation and execution characteristics may differ. To address these challenges, we propose GAT-QNN, a genetic algorithm (GA)-based framework that trains a macroCircuit (search space) by iteratively sampling microCircuits (subcircuits), training them, and reintegrating their learned parameters into the macroCircuit. After training, we run an independent GA-driven inference stage that evaluates candidate microCircuits using the trained macroCircuit weights and selects top-performing architectures for deployment. This two-stage approach enables backend-aware microCircuit selection without retraining each candidate architecture and can also reduce computational resources (gate count) by deploying smaller microCircuits derived from the macroCircuit. We validate the approach on MNIST classification (four classes) and report consistent 22-23% test accuracy gains for GA-driven inference across multiple backends.

quant-ph↗

arXiv2026

How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. This paper provides a controlled benchmark of embedding choices for graph classification, comparing classical baselines with quantum-oriented node representations under a unified pipeline. We evaluate two classical baselines alongside quantum-oriented alternatives, including a circuit-defined variational embedding and quantum-inspired embeddings computed via graph operators and linear-algebraic constructions. All variants are trained and tested with the same backbone, stratified splits, identical optimization and early stopping, and consistent metrics. Experiments on five different TU datasets and on QM9 converted to classification via target binning show clear dataset dependence: quantum-oriented embeddings yield the most consistent gains on structure-driven benchmarks, while social graphs with limited node attributes remain well served by classical baselines. The study highlights practical trade-offs between inductive bias, trainability, and stability under a fixed training budget, and offers a reproducible reference point for selecting quantum-oriented embeddings in graph learning.

cs.LG↗

arXiv2026

Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease

Hybrid Quantum Neural Networks (HQNNs) have recently emerged as a promising paradigm for near-term quantum machine learning. However, their practical performance strongly depends on design choices such as classical-to-quantum data encoding, quantum circuit architecture, measurement strategy and shots. In this paper, we present a comprehensive design space exploration of HQNNs for Chronic Kidney Disease (CKD) diagnosis. Using a carefully curated and preprocessed clinical dataset, we benchmark 625 different HQNN models obtained by combining five encoding schemes, five entanglement architectures, five measurement strategies, and five different shot settings. To ensure fair and robust evaluation, all models are trained using 10-fold stratified cross-validation and assessed on a test set using a comprehensive set of metrics, including accuracy, area under the curve (AUC), F1-score, and a composite performance score. Our results reveal strong and non-trivial interactions between encoding choices and circuit architectures, showing that high performance does not necessarily require large parameter counts or complex circuits. In particular, we find that compact architectures combined with appropriate encodings (e.g., IQP with Ring entanglement) can achieve the best trade-off between accuracy, robustness, and efficiency. Beyond absolute performance analysis, we also provide actionable insights into how different design dimensions influence learning behavior in HQNNs.

cs.LG↗

arXiv2026

scaleTRIM: Scalable TRuncation-Based Integer Approximate Multiplier with Linearization and Compensation

In this paper, we propose a scalable approximate multiplier design, scaleTRIM, that approximates the multiplication operation using fitted linear functions, also referred to as linearization. We show that multiplication operations can be completely replaced by low-cost addition and bit-wise shift operations by exploiting linearization. Moreover, our proposed design utilizes a lookup table (LUT)-based compensation unit as a novel error-reduction method. In essence, input operands are truncated to a reduced bit-width representation (i.e., h bits) based on their leading-one positions. Then, a curve-fitting method is employed to map the product term to a linear function. Additionally, a piecewise constant error-correction term is used to reduce the approximation error. To compute the piecewise constant, we divide the function space into M segments and average the errors within each segment. In particular, our multiplier supports various degrees of truncation and error compensation to offer a range of accuracy-efficiency trade-offs. The proposed multiplier improves the Mean Relative Error Distance (MRED) by about 15.2% while satisfying the efficiency constraint and improves the Power Delay Product (PDP) by about 22.8% while satisfying the accuracy and efficiency constraints compared to different state-of-the-art approximate multipliers. From a usability perspective, our evaluation of the proposed design for image classification using Deep Neural Networks (DNNs) demonstrates that scaleTRIM offers a better accuracy-efficiency trade-off than state-of-the-art approximate multiplier designs.

cs.DC↗

arXiv2026

SPATE: Spiking-Phase Adaptive Temporal Encoding for Quantum Machine Learning

Most quantum machine learning (QML) pipelines still rely on static encodings such as angle and amplitude maps, and this limits their ability to handle temporal information. To address this limitation, this paper uses spike-based data representation as an effective encoding mechanism that incorporates temporal structure into quantum feature preparation. Specifically, we propose Spiking-Phase Adaptive Temporal Encoding (SPATE), a novel spike-driven temporal encoding method that converts real-valued tabular features into leaky integrate-and-fire spike trains and maps spike statistics to quantum rotations, augmented with a small set of temporal qubits through controlled phase operations. An encoding-centric evaluation protocol is also introduced to assess representation quality independently of the classifier, covering centered kernel-target alignment (CKTA), Fisher-style separability, inter/intra-class distance ratios, silhouette score, normalized entropy, and pairwise total-variation (TVpair) collapse indicators. Under stratified cross-validation, SPATE yields stronger representations across multiple datasets. For example, SPATE reaches a CKTA of 0.966 and a Fisher score of 7.37 on Blobs, compared with a CKTA of 0.632 and a Fisher score of 0.70 using angle encoding, and achieves a CKTA of 0.506 on Moons, compared with 0.015 using angle or amplitude encoding. These gains translate into stronger hybrid quantum neural network performance within a fixed qubit budget across several tasks, including an accuracy of 0.826 and an AUC of 0.978 for Wine, as well as an accuracy of 0.840 and an AUC of 0.923 for Moons. These results demonstrate that SPATE provides a practical spike-to-phase interface for building more informative quantum feature representations under constrained resources.

quant-ph↗

arXiv2026

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark

Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate the key factors that drive agent success and provide a detailed recipe for building effective LLM-based offensive security agents. First, we present CTFJudge, a framework leveraging LLM as a judge to analyze agent trajectories and provide granular evaluation across CTF solving steps. Second, we propose a novel metric, CTF Competency Index (CCI) for partial correctness, revealing how closely agent solutions align with human-crafted gold standards. Third, we examine how LLM hyperparameters, namely temperature, top-p, and maximum token length, influence agent performance and automated cybersecurity task planning. For rapid evaluation, we present CTFTiny, a curated benchmark of 50 representative CTF challenges across binary exploitation, web, reverse engineering, forensics, and cryptography. Our findings identify optimal multi-agent coordination settings and lay the groundwork for future LLM agent research in cybersecurity. We make CTFTiny open source to public https://github.com/NYU-LLM-CTF/CTFTiny along with CTFJudge on https://github.com/NYU-LLM-CTF/CTFJudge.

cs.CR↗

arXiv2026

TRAPTI: Time-Resolved Analysis for SRAM Banking and Power Gating Optimization in Embedded Transformer Inference

Transformer neural networks achieve state-of-the-art accuracy across language and vision tasks, but their deployment on embedded hardware is hindered by stringent area, latency, and energy constraints. During inference, performance and efficiency are increasingly dominated by the Key--Value (KV) cache, whose memory footprint grows with sequence length, straining on-chip memory utilization. Although existing mechanisms such as Grouped-Query Attention (GQA) reduce KV cache requirements compared to Multi-Head Attention (MHA), effectively exploiting this reduction requires understanding how on-chip memory demand evolves over time. This work presents TRAPTI, a two-stage methodology that combines cycle-level inference simulation with time-resolved analysis of on-chip memory occupancy to guide design decisions. In the first stage, the framework obtains memory occupancy traces and memory access statistics from simulation. In the second stage, the framework leverages the traces to explore banked memory organizations and power-gating configurations in an offline optimization flow. We apply this methodology to GPT-2 XL and DeepSeek-R1-Distill-Qwen-1.5B under the same accelerator configuration, enabling a direct comparison of MHA and GQA memory profiles. The analysis shows that DeepSeek-R1-Distill-Qwen-1.5B exhibits a 2.72x reduction in peak on-chip memory utilization in this setting compared to GPT-2 XL, unlocking further opportunities for power-gating optimization.

cs.AR↗

arXiv2026

QNAS: A Neural Architecture Search Framework for Accurate and Efficient Quantum Neural Networks

Designing quantum neural networks (QNNs) that are both accurate and deployable on NISQ hardware is challenging. Handcrafted ansatze must balance expressivity, trainability, and resource use, while limited qubits often necessitate circuit cutting. Existing quantum architecture search methods primarily optimize accuracy while only heuristically controlling quantum and mostly ignore the exponential overhead of circuit cutting. We introduce QNAS, a neural architecture search framework that unifies hardware aware evaluation, multi objective optimization, and cutting overhead awareness for hybrid quantum classical neural networks (HQNNs). QNAS trains a shared parameter SuperCircuit and uses NSGA-II to optimize three objectives jointly: (i) validation error, (ii) a runtime cost proxy measuring wall clock evaluation time, and (iii) the estimated number of subcircuits under a target qubit budget. QNAS evaluates candidate HQNNs under a few epochs of training and discovers clear Pareto fronts that reveal tradeoffs between accuracy, efficiency, and cutting overhead. Across MNIST, Fashion-MNIST, and Iris benchmarks, we observe that embedding type and CNOT mode selection significantly impact both accuracy and efficiency, with angle-y embedding and sparse entangling patterns outperforming other configurations on image datasets, and amplitude embedding excelling on tabular data (Iris). On MNIST, the best architecture achieves 97.16% test accuracy with a compact 8 qubit, 2 layer circuit; on the more challenging Fashion-MNIST, 87.38% with a 5 qubit, 2 layer circuit; and on Iris, 100% validation accuracy with a 4 qubit, 2 layer circuit. QNAS surfaces these design insights automatically during search, guiding practitioners toward architectures that balance accuracy, resource efficiency, and practical deployability on current hardware.

quant-ph↗

arXiv2026

Scaling Laws for Hybrid Quantum Neural Networks: Depth, Width, and Quantum-Centric Diagnostics

Hybrid quantum neural networks are increasingly explored for classification, yet it remains unclear how their performance and quantum behavior scale with circuit depth and qubit count. We present a controlled scaling study of hybrid quantum-classical classifiers along two axes: (1) increasing the number of quantum layers L at fixed qubits Q, and (2) increasing the number of qubits Q at fixed depth L. Across multiple datasets, we evaluate predictive performance using Accuracy, PR-AUC, Precision, Recall, and F1, and track quantum-specific metrics (QCE, EEE, QGN) to characterize how quantum properties evolve under scaling. Our results summarize scaling trends, saturation regimes, and dataset-dependent sensitivity, and further analyze how quantum metrics relate to predictive performance. This study provides practical guidance for selecting (Q,L) in hybrid QNN classifiers and establishes a consistent evaluation protocol for scaling analysis.

quant-ph↗

arXiv2026

Late Breaking Results: Hardware-Efficient Quantum Reservoir Computing via Quantized Readout

Due to rising electricity demand, accurate short-term load forecasting is increasingly important for grid stability and efficient energy management, particularly in resource-constrained edge settings. We present a hardware-efficient Quantum Reservoir Computing (QRC) framework based on a fixed, untrained quantum circuit with Chebyshev feature encoding, brickwork entanglement, and single- and two-qubit Pauli measurements, avoiding quantum backpropagation entirely. Using the Tetouan City Power Consumption dataset, we examine the effect of post-training fixed-point quantization on the classical readout layer, with the reservoir architecture selected through a genetic search over 18 candidate configurations. Under finite-shot evaluation, 8-bit and 6-bit quantization maintain forecasting accuracy within 1% of the FP32 baseline while reducing readout memory by 75% and 81%, respectively. These results suggest that quantized readout can improve the hardware efficiency and deployment practicality of QRC for memory-constrained energy forecasting.

cs.ET↗

arXiv2026

AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes

Large language models are rapidly changing how learners acquire and demonstrate cybersecurity skills. However, when human--AI collaboration is allowed, educators still lack validated competition designs and evaluation practices that remain fair and evidence-based. This paper presents a cross-regional study of LLM-centered Capture-the-Flag competitions built on the Cyber Security Awareness Week competition system. To understand how autonomy levels and participants' knowledge backgrounds influence problem-solving performance and learning-related behaviors, we formalize three autonomy levels: human-in-the-loop, autonomous agent frameworks, and hybrid. To enable verification, we require traceable submissions including conversation logs, agent trajectories, and agent code. We analyze multi-region competition data covering an in-class track, a standard track, and a year-long expert track, each targeting participants with different knowledge backgrounds. Using data from the 2025 competition, we compare solve performance across autonomy levels and challenge categories, and observe that autonomous agent frameworks and hybrid achieve higher completion rates on challenges requiring iterative testing and tool interactions. In the in-class track, we classify participants' agent designs and find a preference for lightweight, tool-augmented prompting and reflection-based retries over complex multi-agent architectures. Our results offer actionable guidance for designing LLM-assisted cybersecurity competitions as learning technologies, including autonomy-specific scoring criteria, evidence requirements that support solution verification, and track structures that improve accessibility while preserving reliable evaluation and engagement.

cs.SE↗

arXiv2026

Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models

Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on suppressing or blocking region-specific representations, often creating semantic gaps that inadvertently induce hallucination, where models invent plausible but incorrect objects. In this work, we demonstrate that hallucination arises not from object absence per se, but from semantic discontinuity introduced by such suppression-based attacks. We propose a new class of \emph{background-consistent object concealment} attacks, which hide target objects by re-encoding their visual representations to be statistically and semantically consistent with surrounding background regions. Crucially, our approach preserves token structure and attention flow, avoiding representational voids that trigger hallucination. We present a pixel-level optimization framework that enforces background-consistent re-encoding across multiple transformer layers while preserving global scene semantics. Extensive experiments on state-of-the-art vision-language models show that our method effectively conceals target objects while preserving up to $86\%$ of non-target objects and reducing grounded hallucination by up to $3\times$ compared to attention-suppression-based attacks.

cs.CR↗

arXiv2026

Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detection

Realizing on-device ML-based gesture detection under tight real-time performance, energy and memory constraints is challenging, especially when considering mobile devices with varying battery-power levels. Existing EdgeAI deployments typically rely on a single fixed detector, limiting optimization opportunities. We present Scale-Gest, a novel run-time adaptive gesture detection framework that expands the detector space into a dense family of tiny-YOLO architectures. We introduce multiple novel device-calibrated ACE (Accuracy-Complexity-Energy) profiles by analyzing different model-resolution-stride operating points. A lightweight run-time controller selects an appropriate ACE mode under user-defined and battery constraints, while a motion-aware hand-gesture-tracking ROI gate crops the input for reduced complexity detection. To evaluate performance of our system in real-world car driving scenarios, we introduce a temporally-annotated Driver Simulated Gesture (DSG-18) dataset. Scale-Gest maintains event-level F1 while significantly reducing energy and latency compared to single-detector approaches. On a battery-powered laptop running gesture streams, our ACE controller reduces per-frame energy by 4x (from 6.9 mJ to 1.6 mJ) while maintaining high gesture-detection performance (event-level F1 = 0.8-0.9) and low mean latency (6 ms).

cs.CV↗

arXiv2026

GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations

Vision Language Models (VLMs) exhibit persistent hallucinations in counting tasks, with accuracy substantially lower than other visual reasoning tasks (excluding sentiment). This phenomenon persists even in state-of-the-art reasoning-capable VLMs. Conversely, CNN-based object detection models (ODMs) such as YOLO excel at spatial localization and instance counting with minimal computational overhead. We propose GroundCount, a framework that augments VLMs with explicit spatial grounding from ODMs to mitigate counting hallucinations. In the best case, our prompt-based augmentation strategy achieves 81.3% counting accuracy on the best-performing model (Ovis2.5-2B) - a 6.6pp improvement - while reducing inference time by 22% through elimination of hallucination-driven reasoning loops for stronger models. We conduct comprehensive ablation studies demonstrating that positional encoding is a critical component, being beneficial for stronger models but detrimental for weaker ones. Confidence scores, by contrast, introduce noise for most architectures and their removal improves performance in four of five evaluated models. We further evaluate feature-level fusion architectures, finding that explicit symbolic grounding via structured prompts outperforms implicit feature fusion despite sophisticated cross-attention mechanisms. Our approach yields consistent improvements across four of five evaluated VLM architectures (6.2--7.5pp), with one architecture exhibiting degraded performance due to incompatibility between its iterative reflection mechanisms and structured prompts. These results suggest that counting failures stem from fundamental spatial-semantic integration limitations rather than architecture-specific deficiencies, while highlighting the importance of architectural compatibility in augmentation strategies.

cs.CV↗

arXiv2026

Closing the Loop: Resource-aware Hybrid NAS Guided by Analytical and Hardware-Calibrated Quantum Cost Modeling

Hybrid quantum-classical neural networks (HQNNs) integrate quantum circuits with classical layers, each operating under fundamentally different computational paradigms, which makes hardware resource estimation challenging. The training of quantum circuits on real devices requires thousands of circuit executions, which is impractical on current NISQ devices. Therefore, most HQNNs are evaluated on classical simulators, with hardware cost approximated using floating-point operations (FLOPs). However, FLOPs and existing quantum resource estimation methods (e.g., gate counts) overlook key quantum hardware-specific factors such as gate durations, limited qubit connectivity, and noise, all of which ultimately determine the true cost and scalability of quantum circuits. In this paper, we propose an analytical quantum cost model that estimates quantum hardware resources using real backend calibration data, incorporating gate durations, routing overheads, and noise-induced sampling inefficiencies. To complement this, we develop a classical cost model that converts FLOPs into device-specific throughput, enabling a unified time-based representation of hardware resource cost for both subsystems of HQNNs. Building on these analytical models, we present Hyb-HANAS, a hardware-aware hybrid neural architecture search framework, which jointly optimizes accuracy, hardware cost, and parameter count using NSGA-II. Hyb-HANAS identifies Pareto-optimal trade-offs and cross-domain co-adaptation between classical and quantum components of HQNNs. Beyond NAS, the proposed analytical quantum cost model is broadly applicable to quantum hardware benchmarking, compiler evaluation, and training-time estimation of quantum circuits on NISQ devices.

quant-ph↗

arXiv2026

From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization

Large language models show promise for vulnerability discovery, yet prevailing methods inspect code in isolation, struggle with long contexts, and focus on coarse function- or file-level detections that offer limited guidance to engineers who need precise line-level localization for targeted patches. We introduce T2L, an executable framework for project-level, line-level vulnerability localization that progressively narrows scope from repository modules to exact vulnerable lines via AST-based chunking and evidence-guided refinement. We provide a baseline agent with an Agentic Trace Analyzer (ATA) that fuses runtime evidence such as crash points and stack traces to translate failure symptoms into actionable diagnoses. To enable rigorous evaluation, we introduce T2L-ARVO, an expert-verified 50-case benchmark spanning five crash families in real-world projects. On T2L-ARVO, our baseline achieves up to 58.0% detection and 54.8% line-level localization rate. Together, T2L framework advance LLM-based vulnerability detection toward deployable, precision diagnostics in open-source software workflows.

cs.SE↗

arXiv2026

Comparative Performance Analysis of Quantum Machine Learning Architectures for Credit Card Fraud Detection

As financial fraud becomes increasingly complex, effective detection methods are essential. Quantum Machine Learning (QML) introduces certain capabilities that may enhance both accuracy and efficiency in this area. This study examines how different quantum feature maps and ansatz configurations affect the performance of three QML-based classifiers, the Variational Quantum Classifier (VQC), the Sampler Quantum Neural Network (SQNN), and the Estimator Quantum Neural Network (EQNN), when applied to two non-normalized financial fraud datasets. Different quantum feature map and ansatz configurations are evaluated, revealing distinct performance patterns. The VQC consistently demonstrates strong classification results, achieving an F1-score of 0.88, while the SQNN also delivers promising outcomes. In contrast, the EQNN struggles to produce robust results, emphasizing the challenges presented by non-standardized data. Statistical validation using ANOVA confirms the significance of observed performance differences. Additionally, robustness tests on the best-performing models under five quantum noise types show that they maintain competitive performance, supporting their practical applicability. These findings highlight the importance of careful model configuration in QML-based financial fraud detection. By showing how specific feature maps and ansatz choices influence predictive success, this work guides researchers and practitioners in refining QML approaches for complex financial applications.

quant-ph↗

arXiv2026

QUIET-SR: Quantum Image Enhancement Transformer for Single Image Super-Resolution

Recent advancements in Single-Image Super-Resolution (SISR) using deep learning have significantly improved image restoration quality. However, the high computational cost of processing high-resolution images due to the large number of parameters in classical models, along with the scalability challenges of quantum algorithms for image processing, remains a major obstacle. In this paper, we propose the Quantum Image Enhancement Transformer for Super-Resolution (QUIET-SR), a hybrid framework that extends the Swin transformer architecture with a novel shifted quantum window attention mechanism, built upon variational quantum neural networks. QUIET-SR effectively captures complex residual mappings between low-resolution and high-resolution images, leveraging quantum attention mechanisms to enhance feature extraction and image restoration while requiring a minimal number of qubits, making it suitable for the Noisy Intermediate-Scale Quantum (NISQ) era. We evaluate our framework in MNIST (30.24 PSNR, 0.989 SSIM), FashionMNIST (29.76 PSNR, 0.976 SSIM) and the MedMNIST dataset collection, demonstrating that QUIET-SR achieves PSNR and SSIM scores comparable to state-of-the-art methods while using fewer parameters. Our efficient batching strategy directly enables massive parallelization on multiple QPU's paving the way for practical quantum-enhanced image super-resolution through coordinated QPU-GPU quantum supercomputing.

quant-ph↗