This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…

The paper proposes GloResNet, a lightweight 3D CNN that effectively predicts brain injury in preterm infants using T2-weighted MRI, achieving an average accuracy of 75.18%.

This paper addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception system…

This paper proposes a hybrid CNN-LSTM framework to enhance cyber attack detection and prevention in U.S. critical digital infrastructure by evaluating multiple machine learning models on the CSE-CIC-I…

This paper proposes an improved CNN-LSTM model for IoT intrusion detection, achieving high accuracy by combining spatial and temporal feature learning from network traffic.

Places in the Wild introduces a massive, high-resolution RAW photograph dataset of 67,574 images captured in situ across 810 locations, providing unprecedented detail for ecologically valid vision res…

This study comparatively evaluates four CNN architectures (VGG16, ResNet50, EfficientNetB0, and XceptionNet) for fake image detection, finding VGG16 achieved the highest accuracy (91%).

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

SUPREME is an open-source, multi-GPU framework designed to efficiently and reproducibly evaluate machine unlearning methods for image classification by distributing computationally intensive tasks acr…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

This paper proposes and evaluates two lightweight deep learning-based intelligent Intrusion Detection Systems (CNN and LSTM) to enhance the security of large-scale IoT networks, achieving high classif…

The paper introduces a novel byte-level method to encode network flow records into fixed-size RGB images, significantly improving the performance of Intrusion Detection Systems (IDS) by allowing convo…

The paper introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) to achieve massive, structured compression of deep neural networks, demonstrating compression ratios up to 77,000x…

The paper analyzes congruence-based neural architectures for classifying positive-definite matrices, demonstrating that common semi-orthogonality constraints severely limit the model's expressivity.

The paper proposes an attention-enhanced deep learning framework using EfficientNet and CBAM to achieve high accuracy (93.3%) in classifying peach leaf damage, demonstrating improved robustness under…

The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating re…

The paper proposes a novel Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet) network, which significantly enhances brain tumor segmentation accuracy on benchmark MRI datasets.