相关论文: Shape Defense Against Adversarial Attacks

Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects…

In this paper, we study the robustness of graph convolutional networks (GCNs). Despite the good performance of GCNs on graph semi-supervised learning tasks, previous works have shown that the original GCNs are very unstable to adversarial…

This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very…

Convolutional Neural Networks (CNNs) excel at image classification but remain vulnerable to common corruptions that humans handle with ease. A key reason for this fragility is their reliance on local texture cues rather than global object…

Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…

Given the outstanding progress that convolutional neural networks (CNNs) have made on natural image classification and object recognition problems, it is shown that deep learning methods can achieve very good recognition performance on many…

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount…

Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples". In this work, we propose a new feedforward CNN that improves robustness in the presence of…

Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. Our ablation shows that such…

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…

In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i.e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias. This relative lack of Shape Bias…

Convolutional neural networks (CNNs) have achieved beyond human-level accuracy in the image classification task and are widely deployed in real-world environments. However, CNNs show vulnerability to adversarial perturbations that are…

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack…

This study explores the impact of adversarial perturbations on Convolutional Neural Networks (CNNs) with the aim of enhancing the understanding of their underlying mechanisms. Despite numerous defense methods proposed in the literature,…

Deep learning has made tremendous advances in computer vision tasks such as image classification. However, recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However,…

Convolutional neural networks have recently advanced the state of the art in many tasks including edge and object boundary detection. However, in this paper, we demonstrate that these edge detectors inherit a troubling property of neural…