相关论文: Extreme Classification via Adversarial Softmax App…

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…

Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be affected by the adversary during testing. The learner's goal is to build a…

Even though deep neural networks succeed on many different tasks including semantic segmentation, they lack on robustness against adversarial examples. To counteract this exploit, often adversarial training is used. However, it is known…

Deep learning based automatic modulation classification (AMC) has received significant attention owing to its potential applications in both military and civilian use cases. Recently, data-driven subsampling techniques have been utilized to…

Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples,…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled…

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…

Neural networks trained by empirical risk minimization often suffer from overfitting, especially to specific samples or domains, which leads to poor generalization. Curriculum Learning (CL) addresses this issue by selecting training samples…

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

In reinforcement learning, the softmax parametrization is the standard approach for policies over discrete action spaces. However, it fails to capture the order relationship between actions. Motivated by a real-world industrial problem, we…

Cost-sensitive classification is critical in applications where misclassification errors widely vary in cost. However, over-parameterization poses fundamental challenges to the cost-sensitive modeling of deep neural networks (DNNs). The…

Negative sampling is essential for implicit-feedback-based collaborative filtering, which is used to constitute negative signals from massive unlabeled data to guide supervised learning. The state-of-the-art idea is to utilize hard negative…

Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to…

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Collaborative Filtering (CF) has been successfully used to help users discover the items of interest. Nevertheless, existing CF methods suffer from noisy data issue, which negatively impacts the quality of recommendation. To tackle this…