Related papers: Multi-Label Adversarial Perturbations
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet…
Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural…
Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the…
The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…
Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, thereby rendering the…
Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant…
Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator…
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…
Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this…
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input…
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the…
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adversarial noise contains well-generalizing features and that…
Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adversarial examples, has been shown to deceive neural network…
As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have…
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…
This study explores the robustness of label noise classifiers, aiming to enhance model resilience against noisy data in complex real-world scenarios. Label noise in supervised learning, characterized by erroneous or imprecise labels,…
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…
Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial…
Recent research has demonstrated the brittleness of machine learning systems to adversarial perturbations. However, the studies have been mostly limited to perturbations on images and more generally, classification that does not deal with…