Certified Distributional Robustness on Smoothed Classifiers
- URL: http://arxiv.org/abs/2010.10987v2
- Date: Fri, 30 Apr 2021 07:24:47 GMT
- Title: Certified Distributional Robustness on Smoothed Classifiers
- Authors: Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing
Wang
- Abstract summary: We propose the worst-case adversarial loss over input distributions as a robustness certificate.
By exploiting duality and the smoothness property, we provide an easy-to-compute upper bound as a surrogate for the certificate.
- Score: 27.006844966157317
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 with previous certificates, our certificate better
describes the empirical performance of the smoothed classifiers. By exploiting
duality and the smoothness property, we provide an easy-to-compute upper bound
as a surrogate for the certificate. We adopt a noisy adversarial learning
procedure to minimize the surrogate loss to improve model robustness. We show
that our training method provides a theoretically tighter bound over the
distributional robust base classifiers. Experiments on a variety of datasets
further demonstrate superior robustness performance of our method over the
state-of-the-art certified or heuristic methods.
Related papers
- Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing [87.48628403354351]
certification for machine learning is proving that no adversarial sample can evade a model within a range under certain conditions.
Common certification methods for segmentation use a flat set of fine-grained classes, leading to high abstain rates due to model uncertainty.
We propose a novel, more practical setting, which certifies pixels within a multi-level hierarchy, and adaptively relaxes the certification to a coarser level for unstable components.
arXiv Detail & Related papers (2024-02-13T11:59:43Z) - It's Simplex! Disaggregating Measures to Improve Certified Robustness [32.63920797751968]
This work presents two approaches to improve the analysis of certification mechanisms.
New certification approaches have the potential to more than double the achievable radius of certification.
Empirical evaluation verifies that our new approach can certify $9%$ more samples at noise scale $sigma = 1$.
arXiv Detail & Related papers (2023-09-20T02:16:19Z) - 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) - Confidence-aware Training of Smoothed Classifiers for Certified
Robustness [75.95332266383417]
We use "accuracy under Gaussian noise" as an easy-to-compute proxy of adversarial robustness for an input.
Our experiments show that the proposed method consistently exhibits improved certified robustness upon state-of-the-art training methods.
arXiv Detail & Related papers (2022-12-18T03:57:12Z) - Smooth-Reduce: Leveraging Patches for Improved Certified Robustness [100.28947222215463]
We propose a training-free, modified smoothing approach, Smooth-Reduce.
Our algorithm classifies overlapping patches extracted from an input image, and aggregates the predicted logits to certify a larger radius around the input.
We provide theoretical guarantees for such certificates, and empirically show significant improvements over other randomized smoothing methods.
arXiv Detail & Related papers (2022-05-12T15:26:20Z) - 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) - CROP: Certifying Robust Policies for Reinforcement Learning through
Functional Smoothing [41.093241772796475]
We present the first framework of Certifying Robust Policies for reinforcement learning (CROP) against adversarial state perturbations.
We propose two types of robustness certification criteria: robustness of per-state actions and lower bound of cumulative rewards.
arXiv Detail & Related papers (2021-06-17T07:58:32Z) - 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) - 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)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.