Related papers: PuVAE: A Variational Autoencoder to Purify Adversa…
Deep Neural Networks (DNNs) have shown remarkable performance in a diverse range of machine learning applications. However, it is widely known that DNNs are vulnerable to simple adversarial perturbations, which causes the model to…
Recent work has shown that state-of-the-art models are highly vulnerable to adversarial perturbations of the input. We propose cowboy, an approach to detecting and defending against adversarial attacks by using both the discriminator and…
Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual autoencoders at intermediate layers of the target network.…
Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in downstream tasks such as classification. As previous work…
Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed and added to the…
Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…
Deep neural networks are known to be vulnerable to well-designed adversarial attacks. Although numerous defense strategies have been proposed, many are tailored to the specific attacks or tasks and often fail to generalize across diverse…
The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of…
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…
We propose a novel deterministic purification method to improve adversarial robustness by mapping a potentially adversarial sample toward a nearby sample that lies close to a mode of the data distribution, where classifiers are more…
Machine learning with deep neural networks (DNNs) has become one of the foundation techniques in many safety-critical systems, such as autonomous vehicles and medical diagnosis systems. DNN-based systems, however, are known to be vulnerable…
Despite the enormous performance of deepneural networks (DNNs), recent studies have shown theirvulnerability to adversarial examples (AEs), i.e., care-fully perturbed inputs designed to fool the targetedDNN. Currently, the literature is…
Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…
Automatic speaker verification (ASV) systems are highly vulnerable to presentation attacks, also called spoofing attacks. Replay is among the simplest attacks to mount - yet difficult to detect reliably. The generalization failure of…
Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…
Recent work in adversarial attacks has developed provably robust methods for training deep neural network classifiers. However, although they are often mentioned in the context of robustness, deep generative models themselves have received…
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…
Recent work has advocated for the use of deep learning to perform power allocation in the downlink of massive MIMO (maMIMO) networks. Yet, such deep learning models are vulnerable to adversarial attacks. In the context of maMIMO power…
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at…