English
Related papers

Related papers: Generalized No Free Lunch Theorem for Adversarial …

200 papers

This paper studies binary classification in robust one-bit compressed sensing with adversarial errors. It is assumed that the model is overparameterized and that the parameter of interest is effectively sparse. AdaBoost is considered, and,…

Statistics Theory · Mathematics 2021-12-09 Geoffrey Chinot , Felix Kuchelmeister , Matthias Löffler , Sara van de Geer

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to…

Machine Learning · Statistics 2018-09-25 Tom B. Brown , Nicholas Carlini , Chiyuan Zhang , Catherine Olsson , Paul Christiano , Ian Goodfellow

Learning classifiers that are robust to adversarial examples has received a great deal of recent attention. A major drawback of the standard robust learning framework is there is an artificial robustness radius $r$ that applies to all…

Machine Learning · Computer Science 2023-01-19 Robi Bhattacharjee , Kamalika Chaudhuri

We propose a distributionally robust classification model with a fairness constraint that encourages the classifier to be fair in view of the equality of opportunity criterion. We use a type-$\infty$ Wasserstein ambiguity set centered at…

Machine Learning · Computer Science 2021-07-13 Yijie Wang , Viet Anh Nguyen , Grani A. Hanasusanto

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…

Machine Learning · Computer Science 2021-02-11 Jacob M. Springer , Melanie Mitchell , Garrett T. Kenyon

Machine learning models are vulnerable to adversarial perturbations, that when added to an input, can cause high confidence misclassifications. The adversarial learning research community has made remarkable progress in the understanding of…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…

Machine Learning · Computer Science 2024-05-28 Jonathan Peck , Bart Goossens

This paper is concerned with learners who aim to learn patterns in infinite binary sequences: shown longer and longer initial segments of a binary sequence, they either attempt to predict whether the next bit will be a 0 or will be a 1 or…

Logic in Computer Science · Computer Science 2020-09-15 Gordon Belot

Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection, medical diagnosis, or recommender systems often do not…

Machine Learning · Computer Science 2023-12-14 Klim Kireev , Maksym Andriushchenko , Carmela Troncoso , Nicolas Flammarion

Adversarial risk quantifies the performance of classifiers on adversarially perturbed data. Numerous definitions of adversarial risk -- not all mathematically rigorous and differing subtly in the details -- have appeared in the literature.…

Machine Learning · Statistics 2022-01-25 Muni Sreenivas Pydi , Varun Jog

The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account.…

Machine Learning · Computer Science 2020-01-28 Bhanu Garg , Naresh Manwani

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Machine Learning · Computer Science 2019-10-21 Florian Tramèr , Dan Boneh

While adversarial training can improve robust accuracy (against an adversary), it sometimes hurts standard accuracy (when there is no adversary). Previous work has studied this tradeoff between standard and robust accuracy, but only in the…

Machine Learning · Computer Science 2019-08-28 Aditi Raghunathan , Sang Michael Xie , Fanny Yang , John C. Duchi , Percy Liang

Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…

Machine Learning · Computer Science 2019-07-30 Kaiwen Wu , Yaoliang Yu

Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder its applicability in safety-critical domains. These issues…

Machine Learning · Computer Science 2022-06-09 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani

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

The study of adversarial robustness has so far largely focused on perturbations bound in p-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and…

Machine Learning · Computer Science 2019-09-17 Logan Engstrom , Brandon Tran , Dimitris Tsipras , Ludwig Schmidt , Aleksander Madry

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

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary…

Machine Learning · Computer Science 2018-11-16 Sébastien Bubeck , Yin Tat Lee , Eric Price , Ilya Razenshteyn

We demonstrate that learning procedures that rely on aggregated labels, e.g., label information distilled from noisy responses, enjoy robustness properties impossible without data cleaning. This robustness appears in several ways. In the…

Machine Learning · Statistics 2026-05-26 Chen Cheng , John Duchi