Related papers: Jedi: Entropy-based Localization and Removal of Ad…
Adversarial patch attacks create adversarial examples by injecting arbitrary distortions within a bounded region of the input to fool deep neural networks (DNNs). These attacks are robust (i.e., physically-realizable) and universally…
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods, which rely on attack data or prior knowledge, struggle to effectively address a wide range…
Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more primitive…
Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates the performance of adversarial patches for the YOLO object…
Deep neural networks are successfully used in various applications, but show their vulnerability to adversarial examples. With the development of adversarial patches, the feasibility of attacks in physical scenes increases, and the defenses…
Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…
Developing reliable defenses against patch attacks on object detectors has attracted increasing interest. However, we identify that existing defense evaluations lack a unified and comprehensive framework, resulting in inconsistent and…
Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems. However, their conspicuous and easily detectable nature challenge their practicality in real-world setting. To address…
Adversarial patches are images designed to fool otherwise well-performing neural network-based computer vision models. Although these attacks were initially conceived of and studied digitally, in that the raw pixel values of the image were…
The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against…
The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information…
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of experiments showing…
As vision-based machine learning models are increasingly integrated into autonomous and cyber-physical systems, concerns about (physical) adversarial patch attacks are growing. While state-of-the-art defenses can achieve certified…
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…
Recent years have seen an increasing interest in physical adversarial attacks, which aim to craft deployable patterns for deceiving deep neural networks, especially for person detectors. However, the adversarial patterns of existing…
Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part…
While machine learning applications are getting mainstream owing to a demonstrated efficiency in solving complex problems, they suffer from inherent vulnerability to adversarial attacks. Adversarial attacks consist of additive noise to an…
Defending against physical adversarial attacks is a rapidly growing topic in deep learning and computer vision. Prominent forms of physical adversarial attacks, such as overlaid adversarial patches and objects, share similarities with…
Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing…
Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. However, existing research primarily focuses on image pre-processing defenses, which often result in reduced classification accuracy…