Recent research has demonstrated that feature attribution methods for deep networks can
themselves be incorporated into training; these attribution priors optimize for a model whose …

Deep neural networks (DNN) have been shown to be useful in a wide range of applications.
However, they are also known to be vulnerable to adversarial samples. By transforming a …

Two important topics in deep learning both involve incorporating humans into the modeling
process: Model priors transfer information from humans to a model by regularizing the …

Recently, the vulnerability of deep neural network (DNN)-based audio systems to
adversarial attacks has obtained increasing attention. However, the existing audio …

Neural networks are subject to malicious data poisoning attacks affecting the ability of the
model to make accurate predictions. The attacks are generated using adversarial …

Adversarial attacks against neural networks in a regression setting are a critical yet
understudied problem. In this work, we advance the state of the art by investigating …

Abstract The reasons why Deep Neural Networks are susceptible to being fooled by
adversarial examples remains an open discussion. Indeed, many different strategies can be …

Many adversarial attack methods have investigated the security issue of deep learning
models. Previous works on detecting adversarial samples show superior in accuracy but …

Adversarial attacks are the main security issue of deep neural networks. Detecting
adversarial samples is an effective mechanism for defending adversarial attacks. Previous …

In the field of machine learning, traditional regularization methods generally tend to directly
add regularization terms to the loss function. This paper introduces the" Lai loss", a novel …