English
Related papers

Related papers: The Dimpled Manifold Model of Adversarial Examples…

200 papers

Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower…

Machine Learning · Computer Science 2019-10-29 Stefano Recanatesi , Matthew Farrell , Madhu Advani , Timothy Moore , Guillaume Lajoie , Eric Shea-Brown

To achieve near-zero training error in a classification problem, the layers of a feed-forward network have to disentangle the manifolds of data points with different labels, to facilitate the discrimination. However, excessive class…

Machine Learning · Computer Science 2024-02-26 Simone Ciceri , Lorenzo Cassani , Matteo Osella , Pietro Rotondo , Filippo Valle , Marco Gherardi

State-of-the-art neural networks are vulnerable to adversarial examples; they can easily misclassify inputs that are imperceptibly different than their training and test data. In this work, we establish that the use of cross-entropy loss…

Machine Learning · Computer Science 2019-01-25 Kamil Nar , Orhan Ocal , S. Shankar Sastry , Kannan Ramchandran

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

Machine Learning · Statistics 2017-11-23 Ambrish Rawat , Martin Wistuba , Maria-Irina Nicolae

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Hanwei Zhang , Yannis Avrithis , Teddy Furon , Laurent Amsaleg

Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors. This unexpected lack of robustness raises fundamental questions about their…

Computer Vision and Pattern Recognition · Computer Science 2018-02-01 Andras Rozsa , Manuel Gunther , Terrance E. Boult

This work starts with the intention of using mathematics to understand the intriguing vulnerability observed by ~\citet{szegedy2013} within artificial neural networks. Along the way, we will develop some novel tools with applications far…

Machine Learning · Computer Science 2024-07-17 Brian Bell

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

Machine Learning · Computer Science 2018-06-22 Ayan Sinha , Zhao Chen , Vijay Badrinarayanan , Andrew Rabinovich

Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial…

Human-Computer Interaction · Computer Science 2020-01-29 Kelei Cao , Mengchen Liu , Hang Su , Jing Wu , Jun Zhu , Shixia Liu

Deep neural networks achieve remarkable performance in multiple fields. However, after proper training they suffer from an inherent vulnerability against adversarial examples (AEs). In this work we shed light on inner representations of the…

Machine Learning · Computer Science 2022-04-13 Štefan Pócoš , Iveta Bečková , Igor Farkaš

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study the case of binary classification and prove various…

Machine Learning · Computer Science 2020-12-15 Remi Tachet , Mohammad Pezeshki , Samira Shabanian , Aaron Courville , Yoshua Bengio

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Machine Learning · Computer Science 2020-07-13 Anh Bui , Trung Le , He Zhao , Paul Montague , Olivier deVel , Tamas Abraham , Dinh Phung

While the last five years have seen considerable progress in understanding the internal representations of deep learning models, many questions remain. This is especially true when trying to understand the impact of model design choices,…

Machine Learning · Computer Science 2023-12-08 Henry Kvinge , Grayson Jorgenson , Davis Brown , Charles Godfrey , Tegan Emerson

We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination. Inspired by discrepancy measures and two-sample tests between probability distributions, we…

Machine Learning · Computer Science 2017-07-11 Chengtao Li , David Alvarez-Melis , Keyulu Xu , Stefanie Jegelka , Suvrit Sra

Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Hanieh Naderi , Leili Goli , Shohreh Kasaei

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 João Monteiro , Isabela Albuquerque , Zahid Akhtar , Tiago H. Falk

While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility,…

Machine Learning · Computer Science 2020-11-03 Alexander Robey , Hamed Hassani , George J. Pappas

We prove that for a broad class of permutation-equivariant learning rules (including SGD, Adam, and others), the training process induces a bi-Lipschitz mapping between neurons and strongly constrains the topology of the neuron distribution…

Machine Learning · Computer Science 2025-10-06 Yongyi Yang , Tomaso Poggio , Isaac Chuang , Liu Ziyin

The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In our paper, we shed some lights on the practicality and the…

Machine Learning · Statistics 2019-01-28 Huan Zhang , Hongge Chen , Zhao Song , Duane Boning , Inderjit S. Dhillon , Cho-Jui Hsieh

Deep Neural Networks (DNNs) have recently achieved great success in many classification tasks. Unfortunately, they are vulnerable to adversarial attacks that generate adversarial examples with a small perturbation to fool DNN models,…

Machine Learning · Computer Science 2022-07-07 Xiaowei Zhou , Ivor W. Tsang , Jie Yin