Related papers: Rethinking the Effect of Data Augmentation in Adve…
Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…
Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…
Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary,…
Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperceptible adversarial perturbations. While adversarial training (AT) has proven to be an effective defense approach, the AT mechanism for robustness improvement is not…
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models. To mitigate the costs, we propose Guided…
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…
Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…
Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…
Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by…
Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…
Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as…
Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited research conducted in the…
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…
It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…
Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a meta-initialization} of model parameters (that we call meta-model) to rapidly adapt to new…
Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and…
Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…
Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\ell_\infty$ norm-bounded perturbations. Recent extensions in AT have focused on defending against the…