相关论文: Adversarial Lens: Exploiting Attention Layers to G…

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial…

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics,…

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…

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…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

Traditional adversarial attacks typically aim to alter the predicted labels of input images by generating perturbations that are imperceptible to the human eye. However, these approaches often lack explainability. Moreover, most existing…

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can…

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Large Language Models (LLMs), including GPT-3.5, LLaMA, and PaLM, seem to be knowledgeable and able to adapt to many tasks. However, we still cannot completely trust their answers, since LLMs suffer from \textbf{hallucination}\textemdash…

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize…

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and…

Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…

Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning. While previous research verified that adversarial attacks are often fragile and can be defended via image-level processing, it…

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In…

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…