English
Related papers

Related papers: Bridging the Theoretical Gap in Randomized Smoothi…

200 papers

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Machine Learning · Computer Science 2023-09-06 Ruihan Zhang , Peixin Zhang , Jun Sun

Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. It uses the probabilities of predicting the top two most-likely classes around an input point under a…

Machine Learning · Computer Science 2020-10-26 Aounon Kumar , Alexander Levine , Soheil Feizi , Tom Goldstein

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Machine Learning · Computer Science 2023-05-09 Ambar Pal , Jeremias Sulam

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Othmane Laousy , Alexandre Araujo , Guillaume Chassagnon , Marie-Pierre Revel , Siddharth Garg , Farshad Khorrami , Maria Vakalopoulou

State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that can provably…

Machine Learning · Computer Science 2020-06-01 Mao Ye , Chengyue Gong , Qiang Liu

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. Yet, it is still…

Machine Learning · Computer Science 2023-12-13 Ronghui Mu , Leandro Soriano Marcolino , Tianle Zhang , Yanghao Zhang , Xiaowei Huang , Wenjie Ruan

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

Conformal Prediction (CP) has proven to be an effective post-hoc method for improving the trustworthiness of neural networks by providing prediction sets with finite-sample guarantees. However, under adversarial attacks, classical conformal…

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

Machine Learning · Computer Science 2022-06-30 Zhongkai Hao , Chengyang Ying , Yinpeng Dong , Hang Su , Jun Zhu , Jian Song

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique has been proposed…

Machine Learning · Computer Science 2019-06-18 Jeremy M Cohen , Elan Rosenfeld , J. Zico Kolter

Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness guarantees on the…

Machine Learning · Computer Science 2023-07-18 Aounon Kumar , Alexander Levine , Tom Goldstein , Soheil Feizi

Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbed input with…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Hanbin Hong , Yuan Hong

Text classifiers suffer from small perturbations, that if chosen adversarially, can dramatically change the output of the model. Verification methods can provide robustness certificates against such adversarial perturbations, by computing a…

Machine Learning · Computer Science 2025-02-21 Elias Abad Rocamora , Grigorios G. Chrysos , Volkan Cevher

Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. Separately, certified…

Computation and Language · Computer Science 2021-06-22 Yada Pruksachatkun , Satyapriya Krishna , Jwala Dhamala , Rahul Gupta , Kai-Wei Chang

In binary classification and regression problems, it is well understood that Lipschitz continuity and smoothness of the loss function play key roles in governing generalization error bounds for empirical risk minimization algorithms. In…

Machine Learning · Computer Science 2016-09-14 Ambuj Tewari , Sougata Chaudhuri

In this work, we propose a framework to learn feedback control policies with guarantees on closed-loop generalization and adversarial robustness. These policies are learned directly from expert demonstrations, contained in a dataset of…

Machine Learning · Computer Science 2022-11-03 Abed AlRahman Al Makdah , Vishaal Krishnan , Fabio Pasqualetti

Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported both theoretically and empirically, is that robustness demands…

Machine Learning · Computer Science 2024-06-25 Kai Hu , Klas Leino , Zifan Wang , Matt Fredrikson

Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal…

Machine Learning · Computer Science 2026-05-14 Blaise Delattre , Hengyu Wu , Paul Caillon , Wei Yang Bryan Lim , Yang Cao

Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high…

Machine Learning · Computer Science 2017-11-07 Matthias Hein , Maksym Andriushchenko

A vast literature shows that the learning-based visual perception model is sensitive to adversarial noises, but few works consider the robustness of robotic perception models under widely-existing camera motion perturbations. To this end,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Hanjiang Hu , Zuxin Liu , Linyi Li , Jiacheng Zhu , Ding Zhao