Related papers: Universal Adversarial Attacks with Natural Trigger…
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad…
Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…
Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the…
Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment, we do not yet…
Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…
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…
There is great potential for damage from adversarial learning (AL) attacks on machine-learning based systems. In this paper, we provide a contemporary survey of AL, focused particularly on defenses against attacks on statistical…
Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…
The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single…
As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversarial examples are…
Modern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model. Recent works in NLP use rule-based synonym replacement…
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…
Deep learning based models are vulnerable to adversarial attacks. These attacks can be much more harmful in case of targeted attacks, where an attacker tries not only to fool the deep learning model, but also to misguide the model to…
Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of…
Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…
The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…
The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Even though, some form…
Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…
Neural networks are known to be vulnerable to adversarial examples: inputs that are close to natural inputs but classified incorrectly. In order to better understand the space of adversarial examples, we survey ten recent proposals that are…