相关论文: Adversarial Patch

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of…

Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate…

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming 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…

Machine learning is increasingly critical for analysis of the ever-growing corpora of overhead imagery. Advanced computer vision object detection techniques have demonstrated great success in identifying objects of interest such as ships,…

A wide variety of works have explored the reason for the existence of adversarial examples, but there is no consensus on the explanation. We propose to treat the DNN logits as a vector for feature representation, and exploit them to analyze…

We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterally disrupt incidental structure in the image. We demonstrate…

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…

Neural network-based visuomotor policies enable robots to perform manipulation tasks but remain susceptible to perceptual attacks. For example, conventional 2D adversarial patches are effective under fixed-camera setups, where appearance is…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks such as visual perception in autonomous driving. This…

Object detection is an important computer vision task with plenty of real-world applications; therefore, how to enhance its robustness against adversarial attacks has emerged as a crucial issue. However, most of the previous defense methods…

Adversarial patch is one of the important forms of performing adversarial attacks in the physical world. To improve the naturalness and aggressiveness of existing adversarial patches, location-aware patches are proposed, where the patch's…

Adversarial patches threaten visual AI models in the real world. The number of patches in a patch attack is variable and determines the attack's potency in a specific environment. Most existing defenses assume a single patch in the scene,…

In this paper, we study physical adversarial attacks on object detectors in the wild. Previous works mostly craft instance-dependent perturbations only for rigid or planar objects. To this end, we propose to learn an adversarial pattern to…

The previous study has shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversarial attacks are based…

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this…

We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that…