Related papers: Type I Attack for Generative Models
Deep Neural Networks (DNNs) are vulnerable to deliberately crafted adversarial examples. In the past few years, many efforts have been spent on exploring query-optimisation attacks to find adversarial examples of either black-box or…
Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of images. However, the validation of their quality is still…
Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…
In adversarial attacks intended to confound deep learning models, most studies have focused on limiting the magnitude of the modification so that humans do not notice the attack. On the other hand, during an attack against autonomous cars,…
We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial…
Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the…
Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two…
Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…
We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional and whose output range approximates the set of images of…
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…
With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…
Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…
Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…
Recently there has been an enormous interest in generative models for images in deep learning. In pursuit of this, Generative Adversarial Networks (GAN) and Variational Auto-Encoder (VAE) have surfaced as two most prominent and popular…
Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or…
Generative adversarial networks (GAN) are a class of powerful machine learning techniques, where both a generative and discriminative model are trained simultaneously. GANs have been used, for example, to successfully generate "deep fake"…
In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective. We inject a small-scale trainable module between the intermediate layers of the model…
Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks to overcome…
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…
Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…