English
Related papers

Related papers: Robustness Certificates for Sparse Adversarial Att…

200 papers

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Machine Learning · Computer Science 2021-02-24 Elan Rosenfeld , Ezra Winston , Pradeep Ravikumar , J. Zico Kolter

A robustness certificate is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For {\it any} input perturbations with a magnitude smaller than the certificate value, the classification…

Machine Learning · Computer Science 2020-06-02 Sahil Singla , Soheil Feizi

We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the $\ell_p$ ball of radius $\epsilon$ when $p>2$. Although random smoothing has been well understood for the $\ell_2$ case using…

Machine Learning · Computer Science 2020-03-06 Avrim Blum , Travis Dick , Naren Manoj , Hongyang Zhang

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Cryptography and Security · Computer Science 2024-06-12 Xinyu Zhang , Hanbin Hong , Yuan Hong , Peng Huang , Binghui Wang , Zhongjie Ba , Kui Ren

In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms"…

Machine Learning · Computer Science 2022-03-18 Alexander Levine , Soheil Feizi

The robustness of deep neural networks (DNNs) against adversarial example attacks has raised wide attention. For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate. Compared…

Machine Learning · Computer Science 2021-05-03 Jungang Yang , Liyao Xiang , Ruidong Chen , Yukun Wang , Wei Wang , Xinbing Wang

Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…

Machine Learning · Computer Science 2019-02-19 Vincent Tjeng , Kai Xiao , Russ Tedrake

Deep Neural Networks have demonstrated remarkable success in various domains but remain susceptible to adversarial examples, which are slightly altered inputs designed to induce misclassification. While adversarial attacks typically…

Machine Learning · Computer Science 2024-08-29 Weiyou Liu , Zhenyang Li , Weitong Chen

Randomized smoothing is the state-of-the-art approach to construct image classifiers that are provably robust against additive adversarial perturbations of bounded magnitude. However, it is more complicated to construct reasonable…

Computer Vision and Pattern Recognition · Computer Science 2024-08-12 Dmitrii Korzh , Mikhail Pautov , Olga Tsymboi , Ivan Oseledets

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Apostolos Modas

The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical concern for ensuring the suitability of deep neural networks in safety-critical systems. Existing approaches developed for robust OOD detection in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Nasrin Alipour , Seyyed Ali SeyyedSalehi

Adversarial data examples have drawn significant attention from the machine learning and security communities. A line of work on tackling adversarial examples is certified robustness via randomized smoothing that can provide a theoretical…

Machine Learning · Computer Science 2021-08-24 Haowen Lin , Jian Lou , Li Xiong , Cyrus Shahabi

Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features…

Computer Vision and Pattern Recognition · Computer Science 2019-03-26 Cihang Xie , Yuxin Wu , Laurens van der Maaten , Alan Yuille , Kaiming He

The reliable deployment of neural networks in control systems requires rigorous robustness guarantees. In this paper, we obtain tight robustness certificates over convex attack sets for min-max representations of ReLU neural networks by…

Optimization and Control · Mathematics 2023-10-10 Brendon G. Anderson , Samuel Pfrommer , Somayeh Sojoudi

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial or worst-case inputs, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

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

This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (\emph{i.e.} classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of…

Machine Learning · Computer Science 2021-02-23 Rafael Pinot , Laurent Meunier , Florian Yger , Cédric Gouy-Pailler , Yann Chevaleyre , Jamal Atif

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

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized smoothing adds…

Machine Learning · Computer Science 2024-07-17 Ryo Hase , Ye Wang , Toshiaki Koike-Akino , Jing Liu , Kieran Parsons

A recent technique of randomized smoothing has shown that the worst-case (adversarial) $\ell_2$-robustness can be transformed into the average-case Gaussian-robustness by "smoothing" a classifier, i.e., by considering the averaged…

Machine Learning · Computer Science 2021-01-11 Jongheon Jeong , Jinwoo Shin