Center Smoothing: Certified Robustness for Networks with Structured Outputs

2021-02-19 · NeurIPS 2021 12 · Aounon Kumar, Tom Goldstein

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc. We model the output space as a metric space under a distance/similarity function, such as intersection-over-union, perceptual similarity, total variation distance, etc. Such models are used in many machine learning problems like image segmentation, object detection, generative models, image/audio-to-text systems, etc. Based on a robustness technique called randomized smoothing, our $\textit{center smoothing}$ procedure can produce models with the guarantee that the change in the output, as measured by the distance metric, remains small for any norm-bounded adversarial perturbation of the input. We apply our method to create certifiably robust models with disparate output spaces - from sets to images - and show that it yields meaningful certificates without significantly degrading the performance of the base model. Code for our experiments is available at: https://github.com/aounon/center-smoothing.

📄 PDF Abstract BibTeX arXiv:2102.09701

Code (1)

aounon/center-smoothing 공식 구현 pytorch

Tasks

Adversarial Robustness Dimensionality Reduction Image Classification Image Reconstruction Image Segmentation object-detection Object Detection Semantic Segmentation Super-Resolution

RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing

2024-05-14 · Aref Miri Rekavandi, Olga Ohrimenko, Benjamin I. P. Rubinstein

Randomized smoothing has shown promising certified robustness against adversaries in classification tasks. Despite such success with only zeroth-order access to base models, randomized smoothing has not been extended to …

regression valid

Multi-scale Diffusion Denoised Smoothing

2023-10-25 · NeurIPS 2023 11 · Jongheon Jeong, Jinwoo Shin

Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre-trained models. Specifically, one can p…

Adversarial Robustness Denoising

Certified Adversarial Robustness via Randomized Smoothing

2019-02-08 · Jeremy M Cohen, Elan Rosenfeld, J. Zico Kolter

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 ha…

Adversarial Defense Adversarial Robustness Robust classification

Higher-Order Certified Robustness for Regression

2026-07-06 · Jie Zhang, Natalie Frank arxiv

Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers. However, its application to regression remains under-explored and faces unique challenges. Existing regre…

Adversarial Robustness

Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

2019-12-20 · ICLR 2020 1 · Jinyuan Jia, Xiaoyu Cao, Binghui Wang, Neil Zhenqiang Gong

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses…