English
Related papers

Related papers: Image classifiers can not be made robust to small …

200 papers

We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment. So we must have confidence that our models do not over-rely on this assumption. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Isaac Dunn , Laura Hanu , Hadrien Pouget , Daniel Kroening , Tom Melham

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…

Computer Vision and Pattern Recognition · Computer Science 2017-03-10 Seyed-Mohsen Moosavi-Dezfooli , Alhussein Fawzi , Omar Fawzi , Pascal Frossard

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we propose the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-03 Seyed-Mohsen Moosavi-Dezfooli , Alhussein Fawzi , Omar Fawzi , Pascal Frossard , Stefano Soatto

Neural network image classifiers are known to be vulnerable to adversarial images, i.e., natural images which have been modified by an adversarial perturbation specifically designed to be imperceptible to humans yet fool the classifier. Not…

Computer Vision and Pattern Recognition · Computer Science 2016-08-03 Gintare Karolina Dziugaite , Zoubin Ghahramani , Daniel M. Roy

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Machine Learning · Computer Science 2024-09-13 Oliver J. Sutton , Qinghua Zhou , Ivan Y. Tyukin , Alexander N. Gorban , Alexander Bastounis , Desmond J. Higham

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception.…

Machine Learning · Computer Science 2017-03-27 Dan Hendrycks , Kevin Gimpel

We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Andrew Elliott , Stephen Law , Chris Russell

In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Jason Stock , Andy Dolan , Tom Cavey

In image classification tasks, deep learning models are vulnerable to image distortions i.e. their accuracy significantly drops if the input images are distorted. An image-classifier is considered "reliable" if its accuracy on distorted…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Apostolos Modas

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…

Machine Learning · Computer Science 2021-02-11 Jacob M. Springer , Melanie Mitchell , Garrett T. Kenyon

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Machine Learning · Computer Science 2018-05-03 Ludwig Schmidt , Shibani Santurkar , Dimitris Tsipras , Kunal Talwar , Aleksander Mądry

Convolutional neural network image classifiers are defined and the rate of convergence of the misclassification risk of the estimates towards the optimal misclassification risk is analyzed. Here we consider images as random variables with…

Machine Learning · Statistics 2022-05-12 Michael Kohler , Benjamin Walter

Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST dataset that sparse codes can be very sensitive to image distortions, a behavior…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Kyle Luther , H. Sebastian Seung

We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur $\it{unintentionally}$ ("natural errors"), or due to…

Machine Learning · Computer Science 2019-02-04 Yuval Bahat , Michal Irani , Gregory Shakhnarovich

State of the art computer vision models have been shown to be vulnerable to small adversarial perturbations of the input. In other words, most images in the data distribution are both correctly classified by the model and are very close to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Justin Gilmer , Luke Metz , Fartash Faghri , Samuel S. Schoenholz , Maithra Raghu , Martin Wattenberg , Ian Goodfellow

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Image recognition/classification is a widely studied problem, but its reverse problem, image generation, has drawn much less attention until recently. But the vast majority of current methods for image generation require training/retraining…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Haoyang Li

It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify…

Computer Vision and Pattern Recognition · Computer Science 2017-07-13 Jiajun Lu , Hussein Sibai , Evan Fabry , David Forsyth

Despite extensive research since the community learned about adversarial examples 10 years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to be robust to small perturbations of their inputs. Previous…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Bernd Prach , Christoph H. Lampert
‹ Prev 1 2 3 10 Next ›