Related papers: Semantics Preserving Adversarial Learning
In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…
Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution…
Generative adversarial networks (GANs) have shown significant potential in modeling high dimensional distributions of image data, especially on image-to-image translation tasks. However, due to the complexity of these tasks,…
Nowadays, deep learning models have reached incredible performance in the task of image generation. Plenty of literature works address the task of face generation and editing, with human and automatic systems that struggle to distinguish…
Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…
We introduce a new method for generating color images from sketches or edge maps. Current methods either require some form of additional user-guidance or are limited to the "paired" translation approach. We argue that segmentation…
We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…
Despite the rapid development of adversarial machine learning, most adversarial attack and defense researches mainly focus on the perturbation-based adversarial examples, which is constrained by the input images. In comparison with existing…
This work provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with nonlinear projections from input space onto these class manifolds. The…
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which…
Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…
Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…
Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates…
Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled…
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified…
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps…
This paper presents a novel method to deal with the challenging task of generating photographic images conditioned on semantic image descriptions. Our method introduces accompanying hierarchical-nested adversarial objectives inside the…
Machine learning algorithms have been shown to be vulnerable to adversarial manipulation through systematic modification of inputs (e.g., adversarial examples) in domains such as image recognition. Under the default threat model, the…