English
Related papers

Related papers: Sharp Statistical Guarantees for Adversarially Rob…

200 papers

Randomized smoothing (RS) is a well known certified defense against adversarial attacks, which creates a smoothed classifier by predicting the most likely class under random noise perturbations of inputs during inference. While initial work…

Machine Learning · Computer Science 2023-04-21 Soumalya Nandi , Sravanti Addepalli , Harsh Rangwani , R. Venkatesh Babu

This paper proposes a novel non-parametric multidimensional convex regression estimator which is designed to be robust to adversarial perturbations in the empirical measure. We minimize over convex functions the maximum (over Wasserstein…

Statistics Theory · Mathematics 2020-07-28 Jose Blanchet , Peter W. Glynn , Jun Yan , Zhengqing Zhou

Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly…

Computer Vision and Pattern Recognition · Computer Science 2019-05-24 Huaxia Wang , Chun-Nam Yu

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations…

Machine Learning · Statistics 2019-03-26 Arun Sai Suggala , Adarsh Prasad , Vaishnavh Nagarajan , Pradeep Ravikumar

We consider the question of Gaussian mean testing, a fundamental task in high-dimensional distribution testing and signal processing, subject to adversarial corruptions of the samples. We focus on the relative power of different…

Data Structures and Algorithms · Computer Science 2023-07-21 Clément L. Canonne , Samuel B. Hopkins , Jerry Li , Allen Liu , Shyam Narayanan

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…

Machine Learning · Computer Science 2018-06-13 Jonathan Uesato , Brendan O'Donoghue , Aaron van den Oord , Pushmeet Kohli

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Machine Learning · Computer Science 2018-01-16 Bo Luo , Yannan Liu , Lingxiao Wei , Qiang Xu

Robust scatter estimation is a fundamental task in statistics. The recent discovery on the connection between robust estimation and generative adversarial nets (GANs) by Gao et al. (2018) suggests that it is possible to compute depth-like…

Machine Learning · Computer Science 2019-03-06 Chao Gao , Yuan Yao , Weizhi Zhu

We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning…

Machine Learning · Computer Science 2019-06-25 Hongyang Zhang , Yaodong Yu , Jiantao Jiao , Eric P. Xing , Laurent El Ghaoui , Michael I. Jordan

Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the research community, especially when the adversary is…

Machine Learning · Computer Science 2019-01-31 Nic Ford , Justin Gilmer , Nicolas Carlini , Dogus Cubuk

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by…

Machine Learning · Computer Science 2022-11-22 Jiashuo Liu , Zheyan Shen , Peng Cui , Linjun Zhou , Kun Kuang , Bo Li

Adversarial example (AE) is an attack method for machine learning, which is crafted by adding imperceptible perturbation to the data inducing misclassification. In the current paper, we investigated the upper bound of the probability of…

Machine Learning · Computer Science 2025-03-20 Hiroaki Maeshima , Akira Otsuka

Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unexplored. In this paper, we provide new theoretical insights…

Machine Learning · Computer Science 2019-07-29 Yan Li , Ethan X. Fang , Huan Xu , Tuo Zhao

Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have…

Machine Learning · Computer Science 2019-06-04 Emilio Rafael Balda , Arash Behboodi , Niklas Koep , Rudolf Mathar

The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available. However, the high computational cost (e.g., 100 times more than that of the project gradient…

Machine Learning · Computer Science 2022-06-16 Ruize Gao , Jiongxiao Wang , Kaiwen Zhou , Feng Liu , Binghui Xie , Gang Niu , Bo Han , James Cheng

Adversarial training can achieve robustness against adversarial perturbations and has been widely used in machine learning models. This paper delivers a non-asymptotic consistency analysis of the adversarial training procedure under…

Statistics Theory · Mathematics 2024-05-24 Yiling Xie , Xiaoming Huo

We propose an adversarial evaluation framework for sensitive feature inference based on minimum mean-squared error (MMSE) estimation with a finite sample size and linear predictive models. Our approach establishes theoretical lower bounds…

Machine Learning · Statistics 2025-05-15 Monica Welfert , Nathan Stromberg , Mario Diaz , Lalitha Sankar

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

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set $\mathcal{G}$ up to the smallest possible additive term, called the convergence rate. When the…

Statistics Theory · Mathematics 2009-09-09 Jean-Yves Audibert

Robust training methods against perturbations to the input data have received great attention in the machine learning literature. A standard approach in this direction is adversarial training which learns a model using…

Machine Learning · Computer Science 2021-06-22 Farzan Farnia , Amirali Aghazadeh , James Zou , David Tse
‹ Prev 1 4 5 6 7 8 10 Next ›