English
Related papers

Related papers: Adversarial Examples in Multi-Layer Random ReLU Ne…

200 papers

We consider ReLU networks with random weights, in which the dimension decreases at each layer. We show that for most such networks, most examples $x$ admit an adversarial perturbation at an Euclidean distance of…

Machine Learning · Computer Science 2020-10-29 Amit Daniely , Hadas Schacham

A substantial body of empirical work documents the lack of robustness in deep learning models to adversarial examples. Recent theoretical work proved that adversarial examples are ubiquitous in two-layers networks with sub-exponential width…

Machine Learning · Computer Science 2023-01-24 Andrea Montanari , Yuchen Wu

Despite a great deal of research, it is still not well-understood why trained neural networks are highly vulnerable to adversarial examples. In this work we focus on two-layer neural networks trained using data which lie on a low…

Machine Learning · Computer Science 2023-11-17 Odelia Melamed , Gilad Yehudai , Gal Vardi

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Alex Serban , Erik Poll , Joost Visser

Daniely and Schacham recently showed that gradient descent finds adversarial examples on random undercomplete two-layers ReLU neural networks. The term "undercomplete" refers to the fact that their proof only holds when the number of…

Machine Learning · Computer Science 2021-04-13 Sébastien Bubeck , Yeshwanth Cherapanamjeri , Gauthier Gidel , Rémi Tachet des Combes

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in…

Machine Learning · Computer Science 2020-10-20 Honglin Li , Yifei Fan , Frieder Ganz , Anthony Yezzi , Payam Barnaghi

Adversarial examples have been found for various deep as well as shallow learning models, and have at various times been suggested to be either fixable model-specific bugs, or else inherent dataset feature, or both. We present theoretical…

Machine Learning · Computer Science 2023-04-14 Benjamin L. Badger

Deep neural networks have been shown to suffer from a surprising weakness: their classification outputs can be changed by small, non-random perturbations of their inputs. This adversarial example phenomenon has been explained as originating…

Machine Learning · Computer Science 2016-08-30 Thomas Tanay , Lewis Griffin

The reliability of deep learning algorithms is fundamentally challenged by the existence of adversarial examples, which are incorrectly classified inputs that are extremely close to a correctly classified input. We explore the properties of…

Machine Learning · Statistics 2021-07-23 Giacomo De Palma , Bobak T. Kiani , Seth Lloyd

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…

Machine Learning · Computer Science 2019-05-02 Francesco Crecchi , Davide Bacciu , Battista Biggio

Recent works show that adversarial examples exist for random neural networks [Daniely and Schacham, 2020] and that these examples can be found using a single step of gradient ascent [Bubeck et al., 2021]. In this work, we extend this line…

Machine Learning · Computer Science 2022-10-19 Yunjuan Wang , Enayat Ullah , Poorya Mianjy , Raman Arora

The existence of adversarial examples is relatively understood for random fully connected neural networks, but much less so for convolutional neural networks (CNNs). The recent work [Daniely, 2025] establishes that adversarial examples can…

Machine Learning · Computer Science 2026-02-04 Amit Daniely , Idan Mehalel

Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under…

Machine Learning · Computer Science 2020-02-25 Yi Zhang , Orestis Plevrakis , Simon S. Du , Xingguo Li , Zhao Song , Sanjeev Arora

We show that adversarial examples exist for various random convolutional networks, and furthermore, that this is a relatively simple consequence of the isoperimetric inequality on the special orthogonal group $\mathbb{so}(d)$. This extends…

Machine Learning · Computer Science 2025-06-17 Amit Daniely

Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework,…

Machine Learning · Computer Science 2018-12-13 Marc Khoury , Dylan Hadfield-Menell

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense…

Machine Learning · Computer Science 2025-06-17 Furkan Mumcu , Yasin Yilmaz

Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…

Computer Vision and Pattern Recognition · Computer Science 2021-02-24 Kejiang Chen , Yuefeng Chen , Hang Zhou , Chuan Qin , Xiaofeng Mao , Weiming Zhang , Nenghai Yu

Despite significant advances, deep networks remain highly susceptible to adversarial attack. One fundamental challenge is that small input perturbations can often produce large movements in the network's final-layer feature space. In this…

Machine Learning · Computer Science 2023-04-20 Maria-Florina Balcan , Avrim Blum , Dravyansh Sharma , Hongyang Zhang

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…

Computer Vision and Pattern Recognition · Computer Science 2017-10-30 Xin Li , Fuxin Li

The existence of adversarial examples in which an imperceptible change in the input can fool well trained neural networks was experimentally discovered by Szegedy et al in 2013, who called them "Intriguing properties of neural networks".…

Machine Learning · Computer Science 2019-01-31 Adi Shamir , Itay Safran , Eyal Ronen , Orr Dunkelman
‹ Prev 1 2 3 10 Next ›