Related papers: BeamAttack: Generating High-quality Textual Advers…

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding…

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

In social media, neural network models have been applied to hate speech detection, sentiment analysis, etc., but neural network models are susceptible to adversarial attacks. For instance, in a text classification task, the attacker…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Deep neural networks are susceptible to adversarial attacks, which pose a significant threat to their security and reliability in real-world applications. The most notable adversarial attacks are transfer-based attacks, where an adversary…

Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security risks. To improve the robustness of VLMs against adversarial…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the…

This paper introduces a novel adversarial attack method targeting text classification models, termed the Modified Word Saliency-based Adversarial At-tack (MWSAA). The technique builds upon the concept of word saliency to strategically…

Deep neural networks (DNNs) have achieved remarkable success in the field of natural language processing (NLP), leading to widely recognized applications such as ChatGPT. However, the vulnerability of these models to adversarial attacks…

Deep neural networks are widely known to be vulnerable to adversarial examples. However, vanilla adversarial examples generated under the white-box setting often exhibit low transferability across different models. Since adversarial…

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Adversarial samples for images have been extensively studied in the literature. Among many of the attacking methods, gradient-based methods are both effective and easy to compute. In this work, we propose a framework to adapt the gradient…

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…

Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in…

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of…

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human…