Related papers: Boosting Model Resilience via Implicit Adversarial…
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…
Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the…
Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…
Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial…
Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…
Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…
To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentations (e.g., random resizing). Yet, prior work has explored…
Several recent studies have shown that the use of extra in-distribution data can lead to a high level of adversarial robustness. However, there is no guarantee that it will always be possible to obtain sufficient extra data for a selected…
As a part of the Data-Centric AI Competition, we propose a data-centric approach to improve the diversity of the training samples by iterative sampling. The method itself relies strongly on the fidelity of augmented samples and the…
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…
User behavior on online platforms is evolving, reflecting real-world changes in how people post, whether it's helpful messages or hate speech. Models that learn to capture this content can experience a decrease in performance over time due…
Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society. In this study, we…
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…
The quality and size of training set have great impact on the results of deep learning-based face related tasks. However, collecting and labeling adequate samples with high quality and balanced distributions still remains a laborious and…
Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shifts between training and test data. We propose two novel…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
Adversarial examples, or nearly indistinguishable inputs created by an attacker, significantly reduce machine learning accuracy. Theoretical evidence has shown that the high intrinsic dimensionality of datasets facilitates an adversary's…