相关论文: NSA: Naturalistic Support Artifact to Boost Networ…

We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data. NSA integrates Poisson image editing to…

The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on…

Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are biased towards features…

Facial attributes, emerging soft biometrics, must be automatically and reliably extracted from images in order to be usable in stand-alone systems. While recent methods extract facial attributes using deep neural networks (DNNs) trained on…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions…

Artificial Intelligence (AI) tools have become incredibly powerful in generating synthetic images. Of particular concern are generated images that resemble photographs as they aspire to represent real world events. Synthetic photographs may…

In this paper, we propose a natural and robust physical adversarial example attack method targeting object detectors under real-world conditions. The generated adversarial examples are robust to various physical constraints and visually…

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…

Achieving robustness in image segmentation models is challenging due to the fine-grained nature of pixel-level classification. These models, which are crucial for many real-time perception applications, particularly struggle when faced with…

Modern applications such as self-driving cars and drones rely heavily upon robust object detection techniques. However, weather corruptions can hinder the object detectability and pose a serious threat to their navigation and reliability.…

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…

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially…

Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to…

Although state-of-the-art object detection methods have shown compelling performance, models often are not robust to adversarial attacks and out-of-distribution data. We introduce a new dataset, Natural Adversarial Objects (NAO), to…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

The growing incorporation of artificial neural networks (NNs) into many fields, and especially into life-critical systems, is restrained by their vulnerability to adversarial examples (AEs). Some existing defense methods can increase NNs'…

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it…