Related papers: Harmonic Adversarial Attack Method
A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the…
Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society. Many methods have been proposed to detect fake images, but they are vulnerable to adversarial perturbations…
Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…
The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of…
Generating adversarial examples is an intriguing problem and an important way of understanding the working mechanism of deep neural networks. Most existing approaches generated perturbations in the image space, i.e., each pixel can be…
Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…
Image matting and image harmonization are two important tasks in image composition. Image matting, aiming to achieve foreground boundary details, and image harmonization, aiming to make the background compatible with the foreground, are…
We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…
Adversarial attacks meticulously generate minuscule, imperceptible perturbations to images to deceive neural networks. Counteracting these, adversarial purification methods seek to transform adversarial input samples into clean output…
Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original…
Convolutional neural networks have recently advanced the state of the art in many tasks including edge and object boundary detection. However, in this paper, we demonstrate that these edge detectors inherit a troubling property of neural…
Adversarial perturbations are critical for certifying the robustness of deep learning models. A universal adversarial perturbation (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an…
Recent studies show that well-devised perturbations on graph structures or node features can mislead trained Graph Neural Network (GNN) models. However, these methods often overlook practical assumptions, over-rely on heuristics, or…
It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…
Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems. However, perceptual image hashing algorithms are differentiable, and are thus vulnerable to gradient-based adversarial attacks.…
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn…
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…
We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…
Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…
Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes…