arXiv subjects

Sabbir Ahmed

Publications and source records attributed to Sabbir Ahmed.

At least 19 recordsLinked to original sources

arXiv2026

MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models

Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vision-language models still lack. We introduce MemeCULT-1K, a multilingual benchmark of 1,000 South Asian memes in Bengali, English, and Hindi, where each meme is paired with a cultural context note and three human-written explanations, along with a supplementary set of 54 Bengali regional dialect memes. We evaluate thirteen popular Vision Language Models (VLMs) under two settings: meme-only and context-aware. Providing minimal cultural context yields consistent gains across all models and languages: mean SBERT similarity improves from 44.6 to 56.4 (+11.8), BLEURT from 37.3 to 42.3 (+5.0), and LLM-as-a-Judge scores from 2.57 to 3.43 out of 5 (+0.86). Fine-grained error analysis reveals that closed-source models fail mainly on entity and reference misidentification, while open-source models are bottlenecked by broader cultural knowledge gaps, with linguistic and phonological failures proving the most context-resistant across both. These results highlight the difficulty of culturally grounded meme understanding and motivate future work on explicit cultural knowledge integration. Our dataset and code are publicly available at TawsifDipto17/MemeCULT-1K.

cs.CL↗

arXiv2026

AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions

Robust visual recognition in underwater environments remains a significant challenge due to complex distortions such as turbidity, low illumination, and occlusion, which severely degrade the performance of standard vision systems. This paper introduces AQUA20, a comprehensive benchmark dataset comprising 8,171 underwater images across 20 marine species reflecting real-world environmental challenges such as illumination, turbidity, occlusions, etc., providing a valuable resource for underwater visual understanding. Thirteen state-of-the-art deep learning models, including lightweight CNNs (SqueezeNet, MobileNetV2) and transformer-based architectures (ViT, ConvNeXt), were evaluated to benchmark their performance in classifying marine species under challenging conditions. Our experimental results show ConvNeXt achieving the best performance, with a Top-3 accuracy of 98.82% and a Top-1 accuracy of 90.69%, as well as the highest overall F1-score of 88.92% with moderately large parameter size. The results obtained from our other benchmark models also demonstrate trade-offs between complexity and performance. We also provide an extensive explainability analysis using GRAD-CAM and LIME for interpreting the strengths and pitfalls of the models. Our results reveal substantial room for improvement in underwater species recognition and demonstrate the value of AQUA20 as a foundation for future research in this domain. The dataset is publicly available at: https://huggingface.co/datasets/taufiktrf/AQUA20.

cs.CV↗

arXiv2026

Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes

Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their anonymity, as well as their ability to go viral, make them a powerful medium for spreading hate. It remains very difficult to identify such complex and context-dependent hate speech. Although they display excellent performance on multimodal tasks, vision-language models (VLMs) tend to ignore context, irony, and other subtle cues that play a key role in identifying hateful memes. In this work, we present a qualitative analysis of four state-of-the-art VLMs: LLaVA-7B, Qwen-VL, GPT-4o mini, and Claude 3 Haiku. We evaluate these models under zero-shot and few-shot prompting to examine how contextual framing influences their outputs. Our analysis goes beyond simple classification accuracy and focuses on a qualitative evaluation of the models' generated justifications, providing a more in-depth understanding of their thought processes and constraints when dealing with hateful memes.

cs.CL↗

arXiv2026

MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems

Robots need task planning methods to achieve goals that require more than one action. Recently, large pretrained models have demonstrated impressive performance in task planning. For instance, large language models (LLMs) can generate task plans using action and goal descriptions. Despite the rapid progress of large models in robot intelligence, their security implications remain only partially understood, leaving important gaps in the exploration of potential vulnerabilities in LLM-driven robotic planning systems. To investigate such risks, in this paper, we develop MuTRAP, the first multi-trigger trojan attack specifically designed and targeted for LLM-assisted robot task planners. MuTRAP follows the standard practice of LLM usage in robotics where the backbone LLM is typically frozen and hosted in a central server limiting attacker's reach. In contrast, MuTRAP injects backdoor using a small set of task-specific parameters. In addition, we develop a trigger optimization method for selecting multiple-trigger words that are most effective for different robot applications. For instance, one can use unique trigger word "herical" to activate a specific malicious behavior, e.g., cutting hand on a kitchen robot. Through MuTRAP that demonstrates the vulnerability of current LLM-based planners, our goal is to promote the development of secured robot intelligence. Details and demos are provided in: https://mutrap.github.io/MuTRAP/

cs.RO↗

arXiv2026

Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractors

Despite the strong performance of Convolutional Neural Networks (CNNs) in disease classification, their effectiveness often depends on access to large annotated datasets, which is an impractical requirement for emerging or rare conditions such as Monkeypox. To overcome this limitation, we propose a few-shot learning (FSL) framework that employs SimpleShot, a lightweight, non-parametric, inductive classifier, for Monkeypox and pox-like skin disease recognition from limited labeled examples. The proposed pipeline passes the skin lesion images through a frozen, pretrained CNN backbone to obtain feature embeddings, which are then classified via SimpleShot using nearest-centroid comparisons in a normalized embedding space. We systematically benchmark six widely used CNN backbones as feature extractors under consistent experimental settings, enabling fair comparison. Experiments on three publicly available datasets (MSLD v1.0, MSID, and MSLD v2.0) are conducted across 2-way, 4-way, and 6-way tasks with 1-shot, 5-shot, and 10-shot configurations. Among all models, MobileNetV2_100 consistently achieves the highest accuracy. In addition, we present a cross-dataset evaluation for Monkeypox classification, revealing that binary Mpox-vs-Others transfer remains comparatively stable while multi-class performance degrades significantly under domain shift. Together, these results demonstrate the practical utility of combining inductive FSL methods with lightweight CNN backbones and highlight the importance of domain robustness for reliable real-world clinical deployment.

cs.CV↗

arXiv2026

Virtual Try-On for Cultural Clothing: A Benchmarking Study

Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are dominant in western-style clothing and female models, limiting their ability to generalize culturally diverse clothing styles. In this work, we introduce BD-VITON, a virtual try-on dataset focused on Bangladeshi garments, including saree, panjabi and salwar kameez, covering both male and female categories as well. These garments present unique structural challenges such as complex draping, asymmetric layering, and high deformation complexities which are underrepresented in the original VITON dataset. To establish strong baselines, we retrain and evaluate try-on models, namely StableViton, HR-VITON, and VITON-HD on our dataset. Our experiments demonstrate consistent improvements in terms of both quantitative and qualitative analysis, compared to zero shot inference.

cs.CV↗

arXiv2026

SpectroFusion-ViT: A Lightweight Transformer for Speech Emotion Recognition Using Harmonic Mel-Chroma Fusion

Speech is a natural means of conveying emotions, making it an effective method for understanding and representing human feelings. Reliable speech emotion recognition (SER) is central to applications in human-computer interaction, healthcare, education, and customer service. However, most SER methods depend on heavy backbone models or hand-crafted features that fail to balance accuracy and efficiency, particularly for low-resource languages like Bangla. In this work, we present SpectroFusion-ViT, a lightweight SER framework built utilizing EfficientViT-b0, a compact Vision Transformer architecture equipped with self-attention to capture long-range temporal and spectral patterns. The model contains only 2.04M parameters and requires 0.1 GFLOPs, enabling deployment in resource-constrained settings without compromising accuracy. Our pipeline first performs preprocessing and augmentation on raw audio, then extracts Chroma and Mel-frequency cepstral coefficient (MFCC) features. These representations are fused into a complementary time-frequency descriptor that preserves both fine-grained spectral detail and broader harmonic structure. Using transfer learning, EfficientViT-b0 is fine-tuned for multi-class emotion classification. We evaluate the system on two benchmark Bangla emotional speech datasets, SUBESCO and BanglaSER, which vary in speaker diversity, recording conditions, and acoustic characteristics. The proposed approach achieves 92.56% accuracy on SUBESCO and 82.19% on BanglaSER, surpassing existing state-of-the-art methods. These findings demonstrate that lightweight transformer architectures can deliver robust SER performance while remaining computationally efficient for real-world deployment.

cs.SD↗

arXiv2026

From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant modules, yielding a pruned architecture, SNN-SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN-SqueezeNet. Crucially, it narrows the gap with CNN-SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge.

cs.CV↗

arXiv2026

Moral Sycophancy in Vision Language Models

Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on morally grounded visual decision-making remains insufficiently understood. To address this gap, we present the first systematic study of moral sycophancy in VLMs, analyzing ten widely-used models on the Moralise and M^3oralBench datasets under explicit user disagreement. Our results reveal that VLMs frequently produce morally incorrect follow-up responses even when their initial judgments are correct, and exhibit a consistent asymmetry: models are more likely to shift from morally right to morally wrong judgments than the reverse when exposed to user-induced bias. Follow-up prompts generally degrade performance on Moralise, while yielding mixed or even improved accuracy on M^3oralBench, highlighting dataset-dependent differences in moral robustness. Evaluation using Error Introduction Rate (EIR) and Error Correction Rate (ECR) reveals a clear trade-off: models with stronger error-correction capabilities tend to introduce more reasoning errors, whereas more conservative models minimize errors but exhibit limited ability to self-correct. Finally, initial contexts with a morally right stance elicit stronger sycophantic behavior, emphasizing the vulnerability of VLMs to moral influence and the need for principled strategies to improve ethical consistency and robustness in multimodal AI systems.

cs.AI↗

arXiv2026

On the Emergence of Linear Behavior in Large-Scale Dynamical Systems via Spatial Averaging

Various natural and engineered systems, from urban traffic flow to the human brain, can be described by large-scale networked dynamical systems. These systems are similar in being comprised of a large number of microscopic subsystems, each with complex nonlinear dynamics and interactions, that collectively give rise to different forms of macroscopic dynamics. Despite significant research, why and how various forms of macroscopic dynamics emerge from underlying micro-dynamics remains largely unknown. In this work we focus on linearity as one of the most fundamental aspects of system dynamics. By extending the theory of mixing sequences, we show that \textit{in a broad class of autonomous nonlinear networked systems, the dynamics of the average of all subsystems' states becomes asymptotically linear as the number of subsystems grows to infinity, provided that, in addition to technical assumptions, pairwise correlations between subsystems decay to 0 as their pairwise distance grows to infinity}. We prove this result when the latter distance is between subsystems' linear indices or spatial locations, and provide extensions to linear time-invariant (LTI) limit dynamics, finite-sample analysis of rates of convergence, and networks of spatially-embedded subsystems with random locations. To our knowledge, this work is the first rigorous analysis of macroscopic linearity in large-scale heterogeneous networked dynamical systems, and provides a solid foundation for further theoretical and empirical analyses in various domains of science and engineering.

math.DS↗

arXiv2025

CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs

The rapid advancement of large language models (LLMs) has sparked growing interest in understanding their security vulnerabilities, particularly Trojan attacks that enable stealthy manipulation of model behavior. Traditional Trojan methods typically alter inputs and/or model weights, relying on white-box assumptions that require access to data or model internal parameters. In this work, we present CacheTrap, the first gray-box Trojan attack targeting the Key-Value (KV) cache of LLMs. This method induces a single-bit flip in the KV cache, serving as a transient trigger. When activated, this trigger causes the model to exhibit targeted actions without changing inputs or model weights. CacheTrap introduces an efficient search algorithm to locate vulnerable positions in the KV cache, independent of model weights or datasets. Extensive experiments on five open-source LLMs show a remarkable 100% attack success rate (with the trigger) while preserving benign accuracy (without the trigger) by flipping just one bit in the KV cache.

cs.CR↗

arXiv2025

DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Data

While deep learning-based architectures have been widely used for correctly detecting and classifying plant diseases, they require large-scale datasets to learn generalized features and achieve state-of-the-art performance. This poses a challenge for such models to obtain satisfactory performance in classifying leaf diseases with limited samples. This work proposes a few-shot learning framework, Domain-adapted Expert Network (DExNet), for plant disease classification that compensates for the lack of sufficient training data by combining observations of a number of expert critics. It starts with extracting the feature embeddings as 'observations' from nine 'critics' that are state-of-the-art pre-trained CNN-based architectures. These critics are 'domain adapted' using a publicly available leaf disease dataset having no overlapping classes with the specific downstream task of interest. The observations are then passed to the 'Feature Fusion Block' and finally to a classifier network consisting of Bi-LSTM layers. The proposed pipeline is evaluated on the 10 classes of tomato leaf images from the PlantVillage dataset, achieving promising accuracies of 89.06%, 92.46%, and 94.07%, respectively, for 5-shot, 10-shot, and 15-shot classification. Furthermore, an accuracy of 98.09+-0.7% has been achieved in 80-shot classification, which is only 1.2% less than state-of-the-art, allowing a 94.5% reduction in the training data requirement. The proposed pipeline also outperforms existing works on leaf disease classification with limited data in both laboratory and real-life conditions in single-domain, mixed-domain, and cross-domain scenarios.

cs.CV↗

arXiv2025

Cochleagram-based Noise Adapted Speaker Identification System for Distorted Speech

Speaker Identification refers to the process of identifying a person using one's voice from a collection of known speakers. Environmental noise, reverberation and distortion make the task of automatic speaker identification challenging as extracted features get degraded thus affecting the performance of the speaker identification (SID) system. This paper proposes a robust noise adapted SID system under noisy, mismatched, reverberated and distorted environments. This method utilizes an auditory features called cochleagram to extract speaker characteristics and thus identify the speaker. A $128$ channel gammatone filterbank with a frequency range from $50$ to $8000$ Hz was used to generate 2-D cochleagrams. Wideband as well as narrowband noises were used along with clean speech to obtain noisy cochleagrams at various levels of signal to noise ratio (SNR). Both clean and noisy cochleagrams of only $-5$ dB SNR were then fed into a convolutional neural network (CNN) to build a speaker model in order to perform SID which is referred as noise adapted speaker model (NASM). The NASM was trained using a certain noise and then was evaluated using clean and various types of noises. Moreover, the robustness of the proposed system was tested using reverberated as well as distorted test data. Performance of the proposed system showed a measurable accuracy improvement over existing neurogram based SID system.

eess.AS↗

arXiv2025

Explainable AI and Machine Learning for Exam-based Student Evaluation: Causal and Predictive Analysis of Socio-academic and Economic Factors

Academic performance depends on a multivariable nexus of socio-academic and financial factors. This study investigates these influences to develop effective strategies for optimizing students' CGPA. To achieve this, we reviewed various literature to identify key influencing factors and constructed an initial hypothetical causal graph based on the findings. Additionally, an online survey was conducted, where 1,050 students participated, providing comprehensive data for analysis. Rigorous data preprocessing techniques, including cleaning and visualization, ensured data quality before analysis. Causal analysis validated the relationships among variables, offering deeper insights into their direct and indirect effects on CGPA. Regression models were implemented for CGPA prediction, while classification models categorized students based on performance levels. Ridge Regression demonstrated strong predictive accuracy, achieving a Mean Absolute Error of 0.12 and a Mean Squared Error of 0.023. Random Forest outperformed in classification, attaining an F1-score near perfection and an accuracy of 98.68%. Explainable AI techniques such as SHAP, LIME, and Interpret enhanced model interpretability, highlighting critical factors such as study hours, scholarships, parental education, and prior academic performance. The study culminated in the development of a web-based application that provides students with personalized insights, allowing them to predict academic performance, identify areas for improvement, and make informed decisions to enhance their outcomes.

cs.LG↗

arXiv2025

VisionTrap: Unanswerable Questions On Visual Data

Visual Question Answering (VQA) has been a widely studied topic, with extensive research focusing on how VLMs respond to answerable questions based on real-world images. However, there has been limited exploration of how these models handle unanswerable questions, particularly in cases where they should abstain from providing a response. This research investigates VQA performance on unrealistically generated images or asking unanswerable questions, assessing whether models recognize the limitations of their knowledge or attempt to generate incorrect answers. We introduced a dataset, VisionTrap, comprising three categories of unanswerable questions across diverse image types: (1) hybrid entities that fuse objects and animals, (2) objects depicted in unconventional or impossible scenarios, and (3) fictional or non-existent figures. The questions posed are logically structured yet inherently unanswerable, testing whether models can correctly recognize their limitations. Our findings highlight the importance of incorporating such questions into VQA benchmarks to evaluate whether models tend to answer, even when they should abstain.

cs.CV↗

arXiv2025

HaSPeR: An Image Repository for Hand Shadow Puppet Recognition

Hand shadow puppetry, also known as shadowgraphy or ombromanie, is a form of theatrical art and storytelling where hand shadows are projected onto flat surfaces to create illusions of living creatures. The skilled performers create these silhouettes by hand positioning, finger movements, and dexterous gestures to resemble shadows of animals and objects. Due to the lack of practitioners and a seismic shift in people's entertainment standards, this art form is on the verge of extinction. To facilitate its preservation and proliferate it to a wider audience, we introduce ${\rm H{\small A}SP{\small E}R}$, a novel dataset consisting of 15,000 images of hand shadow puppets across 15 classes extracted from both professional and amateur hand shadow puppeteer clips. We provide a detailed statistical analysis of the dataset and employ a range of pretrained image classification models to establish baselines. Our findings show a substantial performance superiority of skip-connected convolutional models over attention-based transformer architectures. We also find that lightweight models, such as MobileNetV2, suited for mobile applications and embedded devices, perform comparatively well. We surmise that such low-latency architectures can be useful in developing ombromanie teaching tools, and we create a prototype application to explore this surmission. Keeping the best-performing model ResNet34 under the limelight, we conduct comprehensive feature-spatial, explainability, and error analyses to gain insights into its decision-making process and explore architectural improvements. To the best of our knowledge, this is the first documented dataset and research endeavor to preserve this dying art for future generations, with computer vision approaches. Our code and data are publicly available at https://github.com/Starscream-11813/HaSPeR.

cs.CV↗

arXiv2025

An Integrated Blockchain and IPFS Solution for Secure and Efficient Source Code Repository Hosting using Middleman Approach

Centralized version control systems (VCS) are vital for software development but pose risks of data loss and ownership disputes. While blockchain offers a decentralized alternative, existing solutions are often hindered by high latency, compromising the real-time collaboration essential for modern workflows. This study introduces a novel hybrid architecture combining the security of the Ethereum blockchain and the InterPlanetary File System (IPFS) with two key contributions: 1) Shamir's Secret Sharing (SSS) to create a trust-minimized model for key distribution, and 2) an authoritative-first, optimistic-fallback retrieval protocol utilizing a temporary middleware to decouple the user experience from blockchain confirmation delays. We implemented a full prototype and conducted a comprehensive performance evaluation on the public Sepolia testnet. Our results demonstrate that this architecture not only provides a secure, auditable, and resilient platform for source code hosting but also achieves highly competitive user-perceived performance. Our user-perceived push time reduces submission latency by up to 49% compared to a standard git push for common repository sizes, proving that a well-designed decentralized VCS can balance the core tenets of security and decentralization with the practical need for speed and efficiency.

cs.CR↗

arXiv2025

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer

True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safeguarding model parameters, particularly weights, is critical to ensure the integrity, privacy, and intel-lectual property of AI systems. While software-based pseudo-random number generators are widely used, they lack the unpredictability and resilience offered by hardware-based TRNGs. In this work, we propose a novel and robust Encoding-in-Memory TRNG called EIM-TRNG that leverages the inherent physical randomness in DRAM cell behavior, particularly under RowHammer-induced disturbances, for the first time. We demonstrate how the unpredictable bit-flips generated through carefully controlled RowHammer operations can be harnessed as a reliable entropy source. Furthermore, we apply this TRNG framework to secure DNN weight data by encoding via a combination of fixed and unpredictable bit-flips. The encrypted data is later decrypted using a key derived from the probabilistic flip behavior, ensuring both data confidentiality and model authenticity. Our results validate the effectiveness of DRAM-based entropy extraction for robust, low-cost hardware security and offer a promising direction for protecting machine learning models at the hardware level.

cs.CR↗