Related papers: Breaking the Illusion: Real-world Challenges for A…

Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…

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…

Despite modifying only a small localized input region, adversarial patches can drastically change the prediction of computer vision models. However, prior methods either cannot perform satisfactorily under targeted attack scenarios or fail…

Previous studies have shown the vulnerability of vision transformers to adversarial patches, but these studies all rely on a critical assumption: the attack patches must be perfectly aligned with the patches used for linear projection in…

We introduce an adversarial sample detection algorithm based on image residuals, specifically designed to guard against patch-based attacks. The image residual is obtained as the difference between an input image and a denoised version of…

Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition…

Machine learning models are known to be susceptible to adversarial perturbation. One famous attack is the adversarial patch, a sticker with a particularly crafted pattern that makes the model incorrectly predict the object it is placed on.…

Autonomous flying robots, such as multirotors, often rely on deep learning models that make predictions based on a camera image, e.g. for pose estimation. These models can predict surprising results if applied to input images outside the…

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…

Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored to…

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…

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while…

Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns…

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…

This paper discusses the attack feasibility of Remote Adversarial Patch (RAP) targeting face detectors. The RAP that targets face detectors is similar to the RAP that targets general object detectors, but the former has multiple issues in…

Tracking multiple objects in a continuous video stream is crucial for many computer vision tasks. It involves detecting and associating objects with their respective identities across successive frames. Despite significant progress made in…

Although state-of-the-art object detection methods have shown compelling performance, models often are not robust to adversarial attacks and out-of-distribution data. We introduce a new dataset, Natural Adversarial Objects (NAO), to…

Current ship detection techniques based on remote sensing imagery primarily rely on the object detection capabilities of deep neural networks (DNNs). However, DNNs are vulnerable to adversarial patch attacks, which can lead to…

Recent works showed the vulnerability of image classifiers to adversarial attacks in the digital domain. However, the majority of attacks involve adding small perturbation to an image to fool the classifier. Unfortunately, such procedures…

Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions.…