Abstract--Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we propose a novel threat model referred to as Med-Hammer that combines the Rowhammer hardware fault injection with neural Trojan attacks to compromise the integrity of ViT -based medical imaging systems. Specifically, we demonstrate how malicious bit flips induced via Rowhammer can trigger implanted neural Trojans, leading to targeted misclassification or suppression of critical diagnoses (e.g., tumors or lesions) in medical scans. Through extensive experiments on benchmark medical imaging datasets such as ISIC, Brain T umor, and MedMNIST, we show that such attacks can remain stealthy while achieving high attack success rates about 82.51% and 92.56% in MobileViT and SwinTrans-former, respectively. We further investigate how architectural properties, such as model sparsity, attention weight distribution, and number of features of the layer, impact attack effectiveness. Our findings highlight a critical and underexplored intersection between hardware-level faults and deep learning security in healthcare applications, underscoring the urgent need for robust defenses spanning both model architectures and underlying hardware platforms. In clinical practice, medical imaging plays a central role in detecting, diagnosing, and monitoring a wide range of conditions.

Illegal landfills are posing as a hazardous threat to people all over the world. Due to the arduous nature of manually identifying the location of landfill, many landfills go unnoticed by authorities and later cause dangerous harm to people and environment. Deep learning can play a significant role in identifying these landfills while saving valuable time, manpower and resources. Despite being a burning concern, good quality publicly released datasets for illegal landfill detection are hard to find due to security concerns. However, AerialWaste Dataset is a large collection of 10434 images of Lombardy region of Italy. The images are of varying qualities, collected from three different sources: AGEA Orthophotos, WorldView-3, and Google Earth. The dataset contains professionally curated, diverse and high-quality images which makes it particularly suitable for scalable and impactful research. As we trained several models to compare results, we found complex and heavy models to be prone to overfitting and memorizing training data instead of learning patterns. Therefore, we chose lightweight simpler models which could leverage general features from the dataset. In this study, Mobilenetv2, Googlenet, Densenet, MobileVit and other lightweight deep learning models were used to train and validate the dataset as they achieved significant success with less overfitting. As we saw substantial improvement in the performance using some of these models, we combined the best performing models and came up with an ensemble model. With the help of ensemble and fusion technique, binary classification could be performed on this dataset with 92.33% accuracy, 92.67% precision, 92.33% sensitivity, 92.41% F1 score and 92.71% specificity.

Monkeypox is a viral disease characterized by distinctive skin lesions and has been reported in many countries. The recent global outbreak has emphasized the urgent need for scalable, accessible, and accurate diagnostic solutions to support public health responses. In this study, we developed ITMAINN, an intelligent, AI-driven healthcare system specifically designed to detect Monkeypox from skin lesion images using advanced deep learning techniques. Our system consists of three main components. First, we trained and evaluated several pretrained models using transfer learning on publicly available skin lesion datasets to identify the most effective models. For binary classification (Monkeypox vs. non-Monkeypox), the Vision Transformer, MobileViT, Transformer-in-Transformer, and VGG16 achieved the highest performance, each with an accuracy and F1-score of 97.8%. For multiclass classification, which contains images of patients with Monkeypox and five other classes (chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy), ResNetViT and ViT Hybrid models achieved 92% accuracy, with F1 scores of 92.24% and 92.19%, respectively. The best-performing and most lightweight model, MobileViT, was deployed within the mobile application. The second component is a cross-platform smartphone application that enables users to detect Monkeypox through image analysis, track symptoms, and receive recommendations for nearby healthcare centers based on their location. The third component is a real-time monitoring dashboard designed for health authorities to support them in tracking cases, analyzing symptom trends, guiding public health interventions, and taking proactive measures. This system is fundamental in developing responsive healthcare infrastructure within smart cities. Our solution, ITMAINN, is part of revolutionizing public health management.

This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as teacher models, this framework enables lightweight student models, particularly ResNet8 and ResNet16, to surpass 90% in accuracy, precision, and recall, adhering to the stringent confidence thresholds necessary for reliable classification tasks. Unlike conventional KD methods that rely on static weight distribution, our adaptive weighting mechanism responds to each teacher model's confidence, allowing student models to prioritize more credible sources of knowledge dynamically. Remarkably, ResNet8 delivers substantial efficiency gains, achieving a 97.5% reduction in parameters, a 96.7% decrease in FLOPs, an 86.2% cut in power consumption, and a 63.5% increase in inference speed over MobileViT. This significant optimization of complexity and resource demands establishes ResNet8 as an optimal candidate for EO tasks, combining robust performance with feasibility in deployment. The confidence-based, adaptable KD approach underscores the potential of dynamic distillation strategies to yield high-performing, resource-efficient models tailored for satellite-based EO applications. The reproducible code is accessible on our GitHub repository.

In this work, we compare the performance of deep learning models for classifying the spinodal dataset. We evaluate state-of-the-art models (MobileViT, NAT, EfficientNet, CNN), alongside several ensemble models (majority voting, AdaBoost). Additionally, we explore the dataset in a transformed color space. Our findings show that NAT and MobileViT outperform other models, achieving the highest metrics-accuracy, AUC, and F1 score on both training and testing data (NAT: 94.65, 0.98, 0.94; MobileViT: 94.20, 0.98, 0.94), surpassing the earlier CNN model (88.44, 0.95, 0.88). We also discuss failure cases for the top performing models.

Numerous techniques have been meticulously designed to achieve optimal architectures for convolutional neural networks (CNNs), yet a comparable focus on vision transformers (ViTs) has been somewhat lacking. Despite the remarkable success of ViTs in various vision tasks, their heavyweight nature presents challenges of computational costs. In this paper, we leverage the Gaussian process to systematically explore the nonlinear and uncertain relationship between performance and global architecture factors of MobileViT, such as resolution, width, and depth including the depth of in-verted residual blocks and the depth of ViT blocks, and joint factors including resolution-depth and resolution-width. We present design principles twisting magic 4D cube of the global architecture factors that minimize model sizes and computational costs with higher model accuracy. We introduce a formula for downsizing architectures by iteratively deriving smaller MobileViT V2, all while adhering to a specified constraint of multiply-accumulate operations (MACs). Experiment results show that our formula significantly outperforms CNNs and mobile ViTs across diversified datasets

The paper proposes an efficient structure for enhancing the performance of mobile-friendly vision transformer with small computational overhead. The vision transformer (ViT) is very attractive in that it reaches outperforming results in image classification, compared to conventional convolutional neural networks (CNNs). Due to its need of high computational resources, MobileNet-based ViT models such as MobileViT-S have been developed. However, their performance cannot reach the original ViT model. The proposed structure relieves the above weakness by storing the information from early attention stages and reusing it in the final classifier. This paper is motivated by the idea that the data itself from early attention stages can have important meaning for the final classification. In order to reuse the early information in attention stages, the average pooling results of various scaled features from early attention stages are used to expand channels in the fully-connected layer of the final classifier. It is expected that the inductive bias introduced by the averaged features can enhance the final performance. Because the proposed structure only needs the average pooling of features from the attention stages and channel expansions in the final classifier, its computational and storage overheads are very small, keeping the benefits of low-cost MobileNet-based ViT (MobileViT). Compared with the original MobileViTs on the ImageNet dataset, the proposed ExMobileViT has noticeable accuracy enhancements, having only about 5% additional parameters.

NLP-based computer vision models, particularly vision transformers, have been shown to outperform CNN models in many imaging tasks. However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images. In this study, we developed digital pathology pipelines to benchmark the five most recently proposed NLP models (vision transformer (ViT), Swin Transformer, MobileViT, CMT, and Sequencer2D) and four popular CNN models (ResNet18, ResNet50, MobileNetV2, and EfficientNet) to predict biomarkers in colorectal cancer (microsatellite instability, CpG island methylator phenotype, and BRAF mutation). Hematoxylin and eosin-stained whole-slide images from Molecular and Cellular Oncology and The Cancer Genome Atlas were used as training and external validation datasets, respectively. Cross-study external validations revealed that the NLP-based models significantly outperformed the CNN-based models in biomarker prediction tasks, improving the overall prediction and precision up to approximately 10% and 26%, respectively. Notably, compared with existing models in the current literature using large training datasets, our NLP models achieved state-of-the-art predictions for all three biomarkers using a relatively small training dataset, suggesting that large training datasets are not a prerequisite for NLP models or transformers, and NLP may be more suitable for clinical studies in which small training datasets are commonly collected. The superior performance of Sequencer2D suggests that further research and innovation on both transformer and bidirectional long short-term memory architectures are warranted in the field of digital pathology. NLP models can replace classic CNN architectures and become the new workhorse backbone in the field of digital pathology.

Human Activity Recognition (HAR) on mobile devices has shown to be achievable with lightweight neural models learned from data generated by the user's inertial measurement units (IMUs). Most approaches for instanced-based HAR have used Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), or a combination of the two to achieve state-of-the-art results with real-time performances. Recently, the Transformers architecture in the language processing domain and then in the vision domain has pushed further the state-of-the-art over classical architectures. However, such Transformers architecture is heavyweight in computing resources, which is not well suited for embedded applications of HAR that can be found in the pervasive computing domain. In this study, we present Human Activity Recognition Transformer (HART), a lightweight, sensor-wise transformer architecture that has been specifically adapted to the domain of the IMUs embedded on mobile devices. Our experiments on HAR tasks with several publicly available datasets show that HART uses fewer FLoating-point Operations Per Second (FLOPS) and parameters while outperforming current state-of-the-art results. Furthermore, we present evaluations across various architectures on their performances in heterogeneous environments and show that our models can better generalize on different sensing devices or on-body positions.

On the ImageNet-1k dataset, MobileViT achieves top-1 accuracy of 78.4% with about 6 million parameters, which is 3.2% and 6.2% more accurate than MobileNetv3 (CNN-based) and DeIT (ViT-based) for a similar number of parameters.