English
Related papers

Related papers: Adversarial Classification: Necessary conditions a…

200 papers

Adversarial training has gained great popularity as one of the most effective defenses for deep neural network and more generally for gradient-based machine learning models against adversarial perturbations on data points. This paper…

Machine Learning · Computer Science 2023-05-25 Haotian Gu , Xin Guo , Xinyu Li

Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or classifier-specific basis. In this work, we take a holistic…

Machine Learning · Computer Science 2020-02-26 Yao-Yuan Yang , Cyrus Rashtchian , Yizhen Wang , Kamalika Chaudhuri

Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a sub-optimal discriminator can still drive the two apart.…

Machine Learning · Computer Science 2020-02-21 Shangyuan Tong , Timur Garipov , Tommi Jaakkola

We study three models of the problem of adversarial training in multiclass classification designed to construct robust classifiers against adversarial perturbations of data in the agnostic-classifier setting. We prove the existence of Borel…

Machine Learning · Computer Science 2023-05-30 Nicolas Garcia Trillos , Matt Jacobs , Jakwang Kim

This paper tackles the problem of adversarial examples from a game theoretic point of view. We study the open question of the existence of mixed Nash equilibria in the zero-sum game formed by the attacker and the classifier. While previous…

Computer Science and Game Theory · Computer Science 2021-02-16 Laurent Meunier , Meyer Scetbon , Rafael Pinot , Jamal Atif , Yann Chevaleyre

Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success. Two distinct categories of samples to which…

Machine Learning · Computer Science 2018-12-11 Partha Ghosh , Arpan Losalka , Michael J Black

The purpose of this paper is to establish the first and second order necessary conditions for stochastic optimal controls in infinite dimensions. The control system is governed by a stochastic evolution equation, in which both drift and…

Optimization and Control · Mathematics 2018-12-27 Hélène Frankowska , Xu Zhang

We explore rigorous, systematic, and controlled experimental evaluation of adversarial examples in the real world and propose a testing regimen for evaluation of real world adversarial objects. We show that for small scene/ environmental…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Brett Jefferson , Carlos Ortiz Marrero

In this work, we formulate a novel framework for adversarial robustness using the manifold hypothesis. This framework provides sufficient conditions for defending against adversarial examples. We develop an adversarial purification method…

Machine Learning · Computer Science 2023-12-22 Zhaoyuan Yang , Zhiwei Xu , Jing Zhang , Richard Hartley , Peter Tu

Past work exploring adversarial vulnerability have focused on situations where an adversary can perturb all dimensions of model input. On the other hand, a range of recent works consider the case where either (i) an adversary can perturb a…

Machine Learning · Computer Science 2023-04-12 Charles Godfrey , Henry Kvinge , Elise Bishoff , Myles Mckay , Davis Brown , Tim Doster , Eleanor Byler

We establish an equivalence between a family of adversarial training problems for non-parametric binary classification and a family of regularized risk minimization problems where the regularizer is a nonlocal perimeter functional. The…

Machine Learning · Computer Science 2023-02-13 Leon Bungert , Nicolás García Trillos , Ryan Murray

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…

Artificial Intelligence · Computer Science 2022-05-04 Thibault Simonetto , Salijona Dyrmishi , Salah Ghamizi , Maxime Cordy , Yves Le Traon

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Machine Learning · Statistics 2018-02-28 Lei Wu , Zhanxing Zhu , Cheng Tai , Weinan E

The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems. This uncertainty has, in turn, lead to considerable research effort in…

Machine Learning · Computer Science 2019-08-02 Christina Göpfert , Jan Philip Göpfert , Barbara Hammer

We prove an exponential separation for the sample complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model. We then show that this separation has interesting implications for adversarial…

Machine Learning · Computer Science 2021-02-19 Grzegorz Głuch , Rüdiger Urbanke

In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a proxy for minimizing the $0/1$ loss in the presence of an…

Machine Learning · Computer Science 2022-05-23 Laurent Meunier , Raphaël Ettedgui , Rafael Pinot , Yann Chevaleyre , Jamal Atif

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Samet Akcay , Amir Atapour-Abarghouei , Toby P. Breckon

Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples. Inspired by the observation that the intrinsic dimension of image data is much smaller than its pixel space dimension and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Yao Li , Martin Renqiang Min , Wenchao Yu , Cho-Jui Hsieh , Thomas C. M. Lee , Erik Kruus

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…

Machine Learning · Computer Science 2020-07-07 Sicheng Zhu , Xiao Zhang , David Evans

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yujie Li , Yanbin Wang , Haitao Xu , Bin Liu , Jianguo Sun , Zhenhao Guo , Wenrui Ma