English
Related papers

Related papers: Adversarial Smoothed Analysis

200 papers

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Machine Learning · Computer Science 2019-02-25 Gavin Weiguang Ding , Kry Yik Chau Lui , Xiaomeng Jin , Luyu Wang , Ruitong Huang

Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbations can be found for…

Machine Learning · Computer Science 2023-08-14 Raphael Olivier , Bhiksha Raj

We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…

Machine Learning · Computer Science 2020-07-29 Jirong Yi , Raghu Mudumbai , Weiyu Xu

In this paper we give a smooth linearization theorem for nonautonomous difference equations with a nonuniform strong exponential dichotomy. The linear part of such a nonautonomous difference equation is defined by a sequence of invertible…

Dynamical Systems · Mathematics 2019-07-09 Davor Dragicevic , Weinian Zhang , Wenmeng Zhang

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

Adversarial training may be regarded as standard training with a modified loss function. But its generalization error appears much larger than standard training under standard loss. This phenomenon, known as robust overfitting, has…

Machine Learning · Computer Science 2024-02-13 Runzhi Tian , Yongyi Mao

This paper is devoted to the estimators of the mean that provide strong non-asymptotic guarantees under minimal assumptions on the underlying distribution. The main ideas behind proposed techniques are based on bridging the notions of…

Statistics Theory · Mathematics 2019-05-07 Stanislav Minsker

We consider a robust estimation of linear regression coefficients. In this note, we focus on the case where the covariates are sampled from an $L$-subGaussian distribution with unknown covariance, the noises are sampled from a distribution…

Statistics Theory · Mathematics 2024-05-27 Takeyuki Sasai , Hironori Fujisawa

We study the consistency of surrogate risks for robust binary classification. It is common to learn robust classifiers by adversarial training, which seeks to minimize the expected $0$-$1$ loss when each example can be maliciously corrupted…

Machine Learning · Computer Science 2025-10-09 Natalie Frank , Jonathan Niles-Weed

Randomized smoothing is the dominant standard for provable defenses against adversarial examples. Nevertheless, this method has recently been proven to suffer from important information theoretic limitations. In this paper, we argue that…

Machine Learning · Computer Science 2022-06-06 Raphael Ettedgui , Alexandre Araujo , Rafael Pinot , Yann Chevaleyre , Jamal Atif

We perform a smoothed analysis of the condition number of rectangular matrices. We prove that, asymptotically, the expected value of this condition number depends only of the elongation of the matrix, and not on the center and variance of…

Numerical Analysis · Mathematics 2011-06-17 Peter Buergisser , Felipe Cucker

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

Machine Learning · Computer Science 2020-01-13 Hadi Salman , Greg Yang , Jerry Li , Pengchuan Zhang , Huan Zhang , Ilya Razenshteyn , Sebastien Bubeck

Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still…

Machine Learning · Computer Science 2023-08-30 Pranjal Awasthi , Natalie S. Frank , Mehryar Mohri

This survey paper is a structured concise summary of four of our recent papers on the stochastic regularity of diffusions that are associated to regular strongly local (but not necessarily symmetric) Dirichlet forms. Here by stochastic…

Probability · Mathematics 2017-10-10 Jiyong Shin , Gerald Trutnau

Randomization as a mean to improve the adversarial robustness of machine learning models has recently attracted significant attention. Unfortunately, much of the theoretical analysis so far has focused on binary classification, providing…

Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter sensitivity and limited robustness. We propose a general…

Machine Learning · Computer Science 2026-05-27 Kukyoung Jang , Taehyun Cho , Junrui Zhang , Ping Xu , Kyungjae Lee

We extend our previous work on sensitivity analysis for the risk ratio and difference contrasts under unmeasured confounding to any contrast. We prove that the bounds produced are still arbitrarily sharp, i.e. practically attainable. We…

Methodology · Statistics 2024-06-13 Jose M. Peña

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at…

Machine Learning · Computer Science 2018-06-07 Liang Tong , Sixie Yu , Scott Alfeld , Yevgeniy Vorobeychik

We derive a fundamental trade-off between standard and adversarial risk in a rather general situation that formalizes the following simple intuition: "If no (nearly) optimal predictor is smooth, adversarial robustness comes at the cost of…

Machine Learning · Statistics 2025-07-01 Sohail Bahmani

For nonautonomous linear difference equations in Banach spaces we show that a very general type of dichotomic behavior persists under small enough additive linear perturbations. By using a new approach, we obtain two general robustness…

Dynamical Systems · Mathematics 2013-09-02 António J. G. Bento , César M. Silva
‹ Prev 1 3 4 5 6 7 10 Next ›