Related papers: Improving Robustness using Generated Data
One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…
Deep learning has excelled in image recognition tasks through neural networks inspired by the human brain. However, the necessity for large models to improve prediction accuracy introduces significant computational demands and extended…
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal…
Adversarial training algorithms have been proved to be reliable to improve machine learning models' robustness against adversarial examples. However, we find that adversarial training algorithms tend to introduce severe disparity of…
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…
Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant…
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…
Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…
"Effective robustness" measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as…
Some recent studies have suggested using GANs for numeric data generation such as to generate data for completing the imbalanced numeric data. Considering the significant difference between the dimensions of the numeric data and images, as…
Training convolutional neural networks (CNNs) with a strict Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients and stable training. While $1$-Lipschitz CNNs can be designed by…
We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no additional training cost for users. We propose a Dataset…
Adversarial examples pose a significant challenge to the robustness, reliability and alignment of deep neural networks. We propose a novel, easy-to-use approach to achieving high-quality representations that lead to adversarial robustness…
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generative Adversarial…
Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting…
Generative adversarial networks (GANs) have achieved remarkable progress in the natural image field. However, when applying GANs in the remote sensing (RS) image generation task, an extraordinary phenomenon is observed: the GAN model is…
Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial…
We propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models. Our method reduces the imbalance between generator and discriminator by partitioning the training data according to data…
In this technical report, we evaluate the adversarial robustness of a very recent method called "Geometry-aware Instance-reweighted Adversarial Training"[7]. GAIRAT reports state-of-the-art results on defenses to adversarial attacks on the…
The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the…