Related papers: Prompt-Guided Environmentally Consistent Adversari…
Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based…
Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly…
The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the…
Deep Neural Networks have been shown to be vulnerable to various kinds of adversarial perturbations. In addition to widely studied additive noise based perturbations, adversarial examples can also be created by applying a per pixel spatial…
Detection of military assets on the ground can be performed by applying deep learning-based object detectors on drone surveillance footage. The traditional way of hiding military assets from sight is camouflage, for example by using…
Physical adversarial examples (PAEs) are regarded as whistle-blowers of real-world risks in deep-learning applications, thus worth further investigation. However, current PAE generation studies show limited adaptive attacking ability to…
Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit various complex downstream tasks, including cross-modal…
Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physically realizable,…
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…
Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show…
Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich…
In recent years, adversarial attacks have drawn more attention for their value on evaluating and improving the robustness of machine learning models, especially, neural network models. However, previous attack methods have mainly focused on…
In recent years, patch representation learning has emerged as a necessary research direction for exploiting the capabilities of machine learning in software generation. These representations have driven significant performance enhancements…
Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images.…
We propose a new class of physics-informed neural networks, called Physics-Informed Generator-Encoder Adversarial Networks, to effectively address the challenges posed by forward, inverse, and mixed problems in stochastic differential…
Gaze redirection is the task of changing the gaze to a desired direction for a given monocular eye patch image. Many applications such as videoconferencing, films, games, and generation of training data for gaze estimation require…
In this paper we propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image. The generator consists of multiple progressive steps. At each step a shadow attention detector is firstly…
Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and AL approaches are often susceptible to adversarial attacks…
In the years since Goodfellow et al. introduced Generative Adversarial Networks (GANs), there has been an explosion in the breadth and quality of generative model applications. Despite this work, GANs still have a long way to go before they…
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are…