Related papers: Consistent Non-Parametric Methods for Adaptive Robustness

Consistent Non-Parametric Methods for Adaptive Robustness

URL: http://arxiv.org/abs/2102.09086v1
Date: Thu, 18 Feb 2021 00:44:07 GMT
Title: Consistent Non-Parametric Methods for Adaptive Robustness
Authors: Robi Bhattacharjee and Kamalika Chaudhuri
Abstract summary: A major drawback of the standard robust learning framework is the imposition of an artificial robustness radius $r$ that applies to all inputs. We propose a new framework for adaptive robustness, called neighborhood preserving robustness.
Score: 26.016647703500887
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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 the imposition of an artificial robustness radius $r$ that applies to all inputs, and ignores the fact that data may be highly heterogeneous. In this paper, we address this limitation by proposing a new framework for adaptive robustness, called neighborhood preserving robustness. We present sufficient conditions under which general non-parametric methods that can be represented as weight functions satisfy our notion of robustness, and show that both nearest neighbors and kernel classifiers satisfy these conditions in the large sample limit.

Related papers

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations [80.86128012438834]
We show for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete. We propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees.
arXiv Detail & Related papers (2024-07-10T09:13:11Z)
Doubly Robust Instance-Reweighted Adversarial Training [107.40683655362285]
We propose a novel doubly-robust instance reweighted adversarial framework. Our importance weights are obtained by optimizing the KL-divergence regularized loss function. Our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance.
arXiv Detail & Related papers (2023-08-01T06:16:18Z)
Characterizing Data Point Vulnerability via Average-Case Robustness [29.881355412540557]
adversarial robustness is a standard framework, which views robustness of predictions through a binary lens. We consider a complementary framework for robustness, called average-case robustness, which measures the fraction of points in a local region. We show empirically that our estimators are accurate and efficient for standard deep learning models.
arXiv Detail & Related papers (2023-07-26T01:10:29Z)
Bounded Robustness in Reinforcement Learning via Lexicographic Objectives [54.00072722686121]
Policy robustness in Reinforcement Learning may not be desirable at any cost. We study how policies can be maximally robust to arbitrary observational noise. We propose a robustness-inducing scheme, applicable to any policy algorithm, that trades off expected policy utility for robustness.
arXiv Detail & Related papers (2022-09-30T08:53:18Z)
Quantifying Robustness to Adversarial Word Substitutions [24.164523751390053]
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. We propose a formal framework to evaluate word-level robustness. metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions.
arXiv Detail & Related papers (2022-01-11T08:18:39Z)
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness [61.212486108346695]
We propose a training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified $ell$-robustness of smoothed classifiers.
arXiv Detail & Related papers (2021-11-17T18:20:59Z)
Adversarial Robustness of Supervised Sparse Coding [34.94566482399662]
We consider a model that involves learning a representation while at the same time giving a precise generalization bound and a robustness certificate. We focus on the hypothesis class obtained by combining a sparsity-promoting encoder coupled with a linear encoder. We provide a robustness certificate for end-to-end classification.
arXiv Detail & Related papers (2020-10-22T22:05:21Z)
A general framework for defining and optimizing robustness [74.67016173858497]
We propose a rigorous and flexible framework for defining different types of robustness properties for classifiers. Our concept is based on postulates that robustness of a classifier should be considered as a property that is independent of accuracy. We develop a very general robustness framework that is applicable to any type of classification model.
arXiv Detail & Related papers (2020-06-19T13:24:20Z)
Consistency Regularization for Certified Robustness of Smoothed Classifiers [89.72878906950208]
A recent technique of randomized smoothing has shown that the worst-case $ell$-robustness can be transformed into the average-case robustness. We found that the trade-off between accuracy and certified robustness of smoothed classifiers can be greatly controlled by simply regularizing the prediction consistency over noise.
arXiv Detail & Related papers (2020-06-07T06:57:43Z)
How to compare adversarial robustness of classifiers from a global perspective [0.0]
Adversarial attacks undermine the reliability of and trust in machine learning models. Point-wise measures for specific threat models are currently the most popular tool for comparing the robustness of classifiers. In this work, we use recently proposed robustness curves to show that point-wise measures fail to capture important global properties.
arXiv Detail & Related papers (2020-04-22T22:07:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.