Related papers: EasyRobust: A Comprehensive and Easy-to-use Toolki…

Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and…

Recent studies have demonstrated that visual recognition models lack robustness to distribution shift. However, current work mainly considers model robustness to 2D image transformations, leaving viewpoint changes in the 3D world less…

Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consistently. Here, we propose to use adversarial attacks as a…

Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are robust to other kinds of changes that occur naturally, such…

Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced…

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as…

This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary…

It is now well known that deep neural networks (DNNs) are vulnerable to adversarial attack. Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence. But…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully…

Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains. It has however been shown that they can be fooled by adversarial examples, i.e., images altered by a…

We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks…

Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against…

It is well-known that deep neural networks (DNNs) have shown remarkable success in many fields. However, when adding an imperceptible magnitude perturbation on the model input, the model performance might get rapid decrease. To address this…

Intelligent Internet of Things (IoT) systems based on deep neural networks (DNNs) have been widely deployed in the real world. However, DNNs are found to be vulnerable to adversarial examples, which raises people's concerns about…

Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to…

Convolutional Neural Networks (CNNs) have advanced existing medical systems for automatic disease diagnosis. However, there are still concerns about the reliability of deep medical diagnosis systems against the potential threats of…

We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that…

We present a new algorithm to train a robust malware detector. Modern malware detectors rely on machine learning algorithms. Now, the adversarial objective is to devise alterations to the malware code to decrease the chance of being…

It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing…

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…