相关论文: Minimizing Perceived Image Quality Loss Through Ad…

We present a method for adversarial attack detection based on the inspection of a sparse set of neurons. We follow the hypothesis that adversarial attacks introduce imperceptible perturbations in the input and that these perturbations…

Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability…

The vulnerability in the algorithm supply chain of deep learning has imposed new challenges to image retrieval systems in the downstream. Among a variety of techniques, deep hashing is gaining popularity. As it inherits the algorithmic…

Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices. Recent best performing image-forensics algorithms greatly benefit from the application of deep learning, but…

As Spiking Neural Networks (SNNs) gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on the adversarial attacks, which is perhaps the most…

Semantic segmentation is a task that traditionally requires a large dataset of pixel-level ground truth labels, which is time-consuming and expensive to obtain. Recent advancements in the weakly-supervised setting show that reasonable…

Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are…

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks…

Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness…

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the…

Adversarial attacks are usually expressed in terms of a gradient-based operation on the input data and model, this results in heavy computations every time an attack is generated. In this work, we solidify the idea of representing…

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…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Recent advancements in deep learning, particularly in medical imaging, have significantly propelled the progress of healthcare systems. However, examining the robustness of medical images against adversarial attacks is crucial due to their…

We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image. We show that it is possible for adversaries to…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Many adversarial attacks belong to the category of dense attacks, which…

Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…

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…