Related papers: Associative Adversarial Learning Based on Selectiv…
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are…
In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…
Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of…
Developments in machine learning interpretability techniques over the past decade have provided new tools to observe the image regions that are most informative for classification and localization in artificial neural networks (ANNs). Are…
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…
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…
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…
Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work…
Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…
Many recent few-shot learning methods concentrate on designing novel model architectures. In this paper, we instead show that with a simple backbone convolutional network we can even surpass state-of-the-art classification accuracy. The…
Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting problem.…
Adversarial examples have revealed the vulnerability of deep learning models and raised serious concerns about information security. The transfer-based attack is a hot topic in black-box attacks that are practical to real-world scenarios…
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…
Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised…
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…
Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the…
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which…
Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization…