相关论文: Ti-Patch: Tiled Physical Adversarial Patch for no-…

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present…

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…

Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial…

With the great success of deep neural networks, adversarial learning has received widespread attention in various studies, ranging from multi-class learning to multi-label learning. However, existing adversarial attacks toward multi-label…

With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…

Quality assessment of videos is crucial for many computer graphics applications, including video games, virtual reality, and augmented reality, where visual performance has a significant impact on user experience. When test videos cannot be…

Image matching approaches have been widely used in computer vision applications in which the image-level matching performance of matchers is critical. However, it has not been well investigated by previous works which place more emphases on…

Adversarial attacks are a potential threat to machine learning models by causing incorrect predictions through imperceptible perturbations to the input data. While these attacks have been extensively studied in unstructured data like…

Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical adversarial attacks. To further demonstrate the potential…

Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…

Image quality assessment (IQA) continues to garner great interest in the research community, particularly given the tremendous rise in consumer video capture and streaming. Despite significant research effort in IQA in the past few decades,…

Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real world artifacts. In physical world attacks, evaluating…

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of…

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…

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…

Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps…

We propose a new method for the visual quality assessment of 360-degree (omnidirectional) videos. The proposed method is based on computing multiple spatio-temporal objective quality features on viewports extracted from 360-degree videos. A…

To effectively evaluate subjective visual quality in weakly-controlled environments, we propose an Adaptive Paired Comparison method based on particle filtering. As our approach requires each sample to be rated only once, the test time…

Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D…