Adversarial system ≈ Adversarial system
View article: GAN（Generative Adversarial Nets）
GAN（Generative Adversarial Nets） Open
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the …
View article
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks Open
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training d…
View article
Generative adversarial networks Open
Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distr…
View article
mixup: Beyond Empirical Risk Minimization Open
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mix…
View article
On Assessing ML Model Robustness: A Methodological Framework (Academic Track) Open
Due to their uncertainty and vulnerability to adversarial attacks, machine learning (ML) models can lead to severe consequences, including the loss of human life, when embedded in safety-critical systems such as autonomous vehicles. Theref…
View article
Generative Adversarial Networks: An Overview Open
Generative adversarial networks (GANs) provide a way to learn deep\nrepresentations without extensively annotated training data. They achieve this\nthrough deriving backpropagation signals through a competitive process\ninvolving a pair of…
View article
Universal Adversarial Perturbations Open
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…
View article
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Open
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training d…
View article
Spectral Normalization for Generative Adversarial Networks Open
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discr…
View article
Self-Attention Generative Adversarial Networks Open
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details a…
View article
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey Open
Deep learning is at the heart of the current rise of artificial intelligence. In the field of computer vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas, deep neural n…
View article
Adversarial Examples in the Physical World Open
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifi…
View article
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks Open
Although deep neural networks (DNNs) have achieved great success in many\ntasks, they can often be fooled by \\emph{adversarial examples} that are\ngenerated by adding small but purposeful distortions to natural examples.\nPrevious studies…
View article
Spectral Normalization for Generative Adversarial Networks Open
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discr…
View article
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling Open
We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional …
View article
Image-to-Image Translation with Conditional Adversarial Networks Open
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this …
View article
Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss Open
The continuous development and extensive use of computed tomography (CT) in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifac…
View article
Towards Deep Learning Models Resistant to Adversarial Attacks Open
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings …
View article
Conditional Adversarial Domain Adaptation Open
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimoda…
View article
Generative Adversarial Text to Image Synthesis Open
Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been develope…
View article
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples Open
Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…
View article
NIPS 2016 Tutorial: Generative Adversarial Networks Open
This report summarizes the tutorial presented by the author at NIPS 2016 on generative adversarial networks (GANs). The tutorial describes: (1) Why generative modeling is a topic worth studying, (2) how generative models work, and how GANs…
View article
Jointly Embedding Multiple Single-Cell Omics Measurements Open
Many single-cell sequencing technologies are now available, but it is still difficult to apply multiple sequencing technologies to the same single cell. In this paper, we propose an unsupervised manifold alignment algorithm, MMD-MA, for in…
View article
Adversarial Examples for Evaluating Reading Comprehension Systems Open
Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…
View article
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets Open
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that…
View article
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Open
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optim…
View article
Ensemble Adversarial Training: Attacks and Defenses Open
Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted …
View article
Generative Adversarial Text to Image Synthesis Open
Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been develope…
View article
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Open
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access man…
View article
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks Open
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant ar…