相关论文: On the Interplay of Convolutional Padding and Adve…

(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotations) entreats both theoretical and empirical understanding.…

Modern neural networks are expected to simultaneously satisfy a host of desirable properties: accurate fitting to training data, generalization to unseen inputs, parameter and computational efficiency, and robustness to adversarial…

Zero padding is often used in convolutional neural networks to prevent the feature map size from decreasing with each layer. However, recent studies have shown that zero padding promotes encoding of absolute positional information, which…

This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that…

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…

Neural networks perform exceedingly well across various machine learning tasks but are not immune to adversarial perturbations. This vulnerability has implications for real-world applications. While much research has been conducted, the…

Mode connectivity provides novel geometric insights on analyzing loss landscapes and enables building high-accuracy pathways between well-trained neural networks. In this work, we propose to employ mode connectivity in loss landscapes to…

Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include…

This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial…

Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural…

The robustness of deep neural networks (DNNs) against adversarial attacks has been studied extensively in hopes of both better understanding how deep learning models converge and in order to ensure the security of these models in…

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…

Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks.…

A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examples are similar to…

In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is…

Adversarial examples provoke weak reliability and potential security issues in deep neural networks. Although adversarial training has been widely studied to improve adversarial robustness, it works in an over-parameterized regime and…

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…

In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to…