相关论文: SITA: Structurally Imperceptible and Transferable …

Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creation of fake news or disturbing content targeting individuals,…

We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features…

Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of unauthorized art style images for AST may infringe on…

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…

Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image…

Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples.…

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical…

Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that are usually used to craft physical-world adversarial examples,…

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this…

Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant…

Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by…

Arbitrary style transfer aims to synthesize a content image with the style of an image to create a third image that has never been seen before. Recent arbitrary style transfer algorithms find it challenging to balance the content structure…

Attention-based arbitrary style transfer methods have gained significant attention recently due to their impressive ability to synthesize style details. However, the point-wise matching within the attention mechanism may overly focus on…

Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink adversarial…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and…

Style transfer enables the seamless integration of artistic styles from a style image into a content image, resulting in visually striking and aesthetically enriched outputs. Despite numerous advances in this field, existing methods did not…

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats…

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an…

We present a novel method for generating robust adversarial image examples building upon the recent `deep image prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in image synthesis. Adversarial…