Related papers: A Universal Adversarial Policy for Text Classifier…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

The previous study has shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversarial attacks are based…

Universal adversarial perturbation attacks are widely used to analyze image classifiers that employ convolutional neural networks. Nowadays, some attacks can deceive image- and video-quality metrics. So sustainability analysis of these…

Text-based adversarial attacks are becoming more commonplace and accessible to general internet users. As these attacks proliferate, the need to address the gap in model robustness becomes imminent. While retraining on adversarial data may…

Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agents to adversarial attacks. However, such direct…

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a…

This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images,…

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications. However, existing adversarial detection methods require access to sufficient training data, which brings…

Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (in domain) and dissimilar (out of domain) instances to those seen in…

The brittleness of deep image classifiers to small adversarial input perturbations has been extensively studied in the last several years. However, the main objective of existing perturbations is primarily limited to change the correctly…

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness…

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of…

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…