相关论文: Unifying Adversarial Training Algorithms with Flex…

Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfitting, i.e., the robustness starts to decrease significantly…

This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively…

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories; gradient masking, robust optimization, and adversarial…

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are…

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (\eg articles with citation…

Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…

Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection, medical diagnosis, or recommender systems often do not…

The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often…

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. One of the most effective strategies to improve robustness is adversarial training. In this paper, we investigate the effect of adversarial…

Despite a great deal of research, it is still not well-understood why trained neural networks are highly vulnerable to adversarial examples. In this work we focus on two-layer neural networks trained using data which lie on a low…

Deep Learning has become interestingly popular in computer vision, mostly attaining near or above human-level performance in various vision tasks. But recent work has also demonstrated that these deep neural networks are very vulnerable to…

As deep learning (DL) models are increasingly being integrated into our everyday lives, ensuring their safety by making them robust against adversarial attacks has become increasingly critical. DL models have been found to be susceptible to…

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

Learning meaningful representations using deep neural networks involves designing efficient training schemes and well-structured networks. Currently, the method of stochastic gradient descent that has a momentum with dropout is one of the…

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a…