English
Related papers

Related papers: Uniform Convergence of Adversarially Robust Classi…

200 papers

We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions from features to…

Machine Learning · Statistics 2020-11-13 Elvis Dohmatob

It is well known that machine learning methods can be vulnerable to adversarially-chosen perturbations of their inputs. Despite significant progress in the area, foundational open problems remain. In this paper, we address several key…

Machine Learning · Computer Science 2024-10-30 Edgar Dobriban , Hamed Hassani , David Hong , Alexander Robey

Motivated by safety-critical applications, test-time attacks on classifiers via adversarial examples has recently received a great deal of attention. However, there is a general lack of understanding on why adversarial examples arise;…

Machine Learning · Statistics 2019-06-20 Yizhen Wang , Somesh Jha , Kamalika Chaudhuri

We study a version of adversarial classification where an adversary is empowered to corrupt data inputs up to some distance $\varepsilon$, using tools from variational analysis. In particular, we describe necessary conditions associated…

Machine Learning · Computer Science 2022-03-14 Nicolas Garcia Trillos , Ryan Murray

Adversarial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models. This can be attributed to either an algorithmic shortcoming or a fundamental property of the training data…

Machine Learning · Computer Science 2021-07-02 Alireza Mousavi Hosseini , Amir Mohammad Abouei , Mohammad Hossein Rohban

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Chaithanya Kumar Mummadi , Thomas Brox , Jan Hendrik Metzen

Despite the wide empirical success of modern machine learning algorithms and models in a multitude of applications, they are known to be highly susceptible to seemingly small indiscernible perturbations to the input data known as…

Machine Learning · Statistics 2022-04-05 Adel Javanmard , Mahdi Soltanolkotabi

This work investigates adversarial training in the context of margin-based linear classifiers in the high-dimensional regime where the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha = n / d$. We introduce…

Machine Learning · Statistics 2026-01-13 Kasimir Tanner , Matteo Vilucchio , Bruno Loureiro , Florent Krzakala

Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. In this paper we study how the…

Machine Learning · Computer Science 2020-02-11 Marc Khoury

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we…

Machine Learning · Computer Science 2018-12-03 Alhussein Fawzi , Hamza Fawzi , Omar Fawzi

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Machine Learning · Computer Science 2019-10-18 Yogesh Balaji , Tom Goldstein , Judy Hoffman

We study the problem of learning predictors that are robust to adversarial examples with respect to an unknown perturbation set, relying instead on interaction with an adversarial attacker or access to attack oracles, examining different…

Machine Learning · Computer Science 2021-02-04 Omar Montasser , Steve Hanneke , Nathan Srebro

We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one predictors, bounds relating the adversarial convex loss to…

Machine Learning · Computer Science 2024-04-30 Justin D. Li , Matus Telgarsky

Despite the enormous success of machine learning models in various applications, most of these models lack resilience to (even small) perturbations in their input data. Hence, new methods to robustify machine learning models seem very…

Machine Learning · Computer Science 2020-10-30 Fariborz Salehi , Babak Hassibi

Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural architectures and…

Machine Learning · Computer Science 2021-03-18 Eitan Richardson , Yair Weiss

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Machine Learning · Computer Science 2023-06-14 Omar Montasser

Why are classifiers in high dimension vulnerable to "adversarial" perturbations? We show that it is likely not due to information theoretic limitations, but rather it could be due to computational constraints. First we prove that, for a…

Machine Learning · Statistics 2018-05-28 Sébastien Bubeck , Eric Price , Ilya Razenshteyn

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Machine Learning · Computer Science 2018-05-03 Ludwig Schmidt , Shibani Santurkar , Dimitris Tsipras , Kunal Talwar , Aleksander Mądry

The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these results can be too general to be applicable to natural data…

Machine Learning · Computer Science 2024-05-28 Ambar Pal , Jeremias Sulam , René Vidal

Despite breakthrough performance, modern learning models are known to be highly vulnerable to small adversarial perturbations in their inputs. While a wide variety of recent \emph{adversarial training} methods have been effective at…

Machine Learning · Computer Science 2020-02-26 Adel Javanmard , Mahdi Soltanolkotabi , Hamed Hassani
‹ Prev 1 2 3 10 Next ›