Related papers: Improving the robustness of ImageNet classifiers u…
Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…
The human visual system is remarkably adept at adapting to changes in the input distribution; a capability modern convolutional neural networks (CNNs) still struggle to match. Drawing inspiration from the developmental trajectory of human…
While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…
Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…
We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and…
Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand…
Adversarial robustness has received increasing attention along with the study of adversarial examples. So far, existing works show that robust models not only obtain robustness against various adversarial attacks but also boost the…
Robustness of neural networks has recently attracted a great amount of interest. The many investigations in this area lack a precise common foundation of robustness concepts. Therefore, in this paper, we propose a rigorous and flexible…
Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…
Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial…
Despite the success of deep-learning models in many tasks, there have been concerns about such models learning shortcuts, and their lack of robustness to irrelevant confounders. When it comes to models directly trained on human faces, a…
Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…
Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers…
Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of…
Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations are previously found to be transferable across different…
The vulnerability of deep neural networks to adversarial examples, which are crafted maliciously by modifying the inputs with imperceptible perturbations to misled the network produce incorrect outputs, reveals the lack of robustness and…
Mammalian brains handle complex reasoning by integrating information across brain regions specialized for particular sensory modalities. This enables improved robustness and generalization versus deep neural networks, which typically…
Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversarial examples in the…
Despite the remarkable success of deep neural networks, significant concerns have emerged about their robustness to adversarial perturbations to inputs. While most attacks aim to ensure that these are imperceptible, physical perturbation…
Humans effortlessly navigate the dynamic visual world, yet deep neural networks (DNNs), despite excelling at many visual tasks, are surprisingly vulnerable to minor image perturbations. Past theories suggest that human visual robustness…