Related papers: ImageNet-Patch: A Dataset for Benchmarking Machine…

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…

Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…

The advent of adversarial patches poses a significant challenge to the robustness of AI models, particularly in the domain of computer vision tasks such as object detection. In contradistinction to traditional adversarial examples, these…

Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the…

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…

Understanding the patterns of misclassified ImageNet images is particularly important, as it could guide us to design deep neural networks (DNN) that generalize better. However, the richness of ImageNet imposes difficulties for researchers…

We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in which an event camera consistently moves around a monitor…

Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this…

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we…

In recent years novel architecture components for image classification have been developed, starting with attention and patches used in transformers. While prior works have analyzed the influence of some aspects of architecture components…

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the…

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…

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified…

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…

We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models. Our framework allows users to customize the types of distortions to be optimally applied to images, which helps…

Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters…

Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…

In this paper we propose a new augmentation technique, called patch augmentation, that, in our experiments, improves model accuracy and makes networks more robust to adversarial attacks. In brief, this data-independent approach creates new…

The vulnerability of deep neural networks to adversarial examples, which are crafted maliciously by modifying the inputs with imperceptible perturbations to misled the network produce incorrect outputs, reveals the lack of robustness and…

Reliable and robust evaluation methods are a necessary first step towards developing machine learning models that are themselves robust and reliable. Unfortunately, current evaluation protocols typically used to assess classifiers fail to…