# Projected Randomized Smoothing for Certified Adversarial Robustness

arXiv: https://arxiv.org/abs/2309.13794 · HTML: https://mlsanity.com/paper/2309.13794/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 64 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 30 of 47)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers](https://mlsanity.com/paper/1906.04584/) (2019)
- [Towards Fast Computation of Certified Robustness for ReLU Networks](https://mlsanity.com/paper/1804.09699/) (2018)
- [Adversarial Risk and the Dangers of Evaluating Against Weak Attacks](https://mlsanity.com/paper/1802.05666/) (2018)
- [Certified Adversarial Robustness with Additive Noise](https://mlsanity.com/paper/1809.03113/) (2018)
- [Semidefinite relaxations for certifying robustness to adversarial examples](https://mlsanity.com/paper/1811.01057/) (2018)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [Randomized Smoothing of All Shapes and Sizes](https://mlsanity.com/paper/2002.08118/) (2020)
- [MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius](https://mlsanity.com/paper/2001.02378/) (2020)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers](https://mlsanity.com/paper/1906.04948/) (2019)
- [Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness](https://mlsanity.com/paper/2002.03239/) (2020)
- [SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving](https://mlsanity.com/paper/1612.01051/) (2016)
- [SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness](https://mlsanity.com/paper/2111.09277/) (2021)
- [Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework](https://mlsanity.com/paper/2002.09169/) (2020)
- [The Dimpled Manifold Model of Adversarial Examples in Machine Learning](https://mlsanity.com/paper/2106.10151/) (2021)
- [Improved, Deterministic Smoothing for L_1 Certified Robustness](https://mlsanity.com/paper/2103.10834/) (2021)
- [Enhancing Robustness of Machine Learning Systems via Data Transformations](https://mlsanity.com/paper/1704.02654/) (2017)
- [Data-Dependent Randomized Smoothing](https://mlsanity.com/paper/2012.04351/) (2020)

## Built on by (most cited first, 11 of 11)

- [MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers](https://mlsanity.com/paper/2402.02263/) (2024)
- [Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing](https://mlsanity.com/paper/2404.09586/) (2024)
- [Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness](https://mlsanity.com/paper/2309.16096/) (2023)
- [Rethinking Randomized Smoothing from the Perspective of Scalability](https://mlsanity.com/paper/2312.12608/) (2023)
- [Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off](https://mlsanity.com/paper/2311.15165/) (2023)
- [CERT-ED: Certifiably Robust Text Classification for Edit Distance](https://mlsanity.com/paper/2408.00728/) (2024)
- [Certified Robustness against Sparse Adversarial Perturbations via Data Localization](https://mlsanity.com/paper/2405.14176/) (2024)
- [Adversarial Examples in Environment Perception for Automated Driving (Review)](https://mlsanity.com/paper/2504.08414/) (2025)
- [RRISE: Robust Radius Inference via a Surrogate Estimator](https://mlsanity.com/paper/2606.02876/) (2026)
- [Representation Matters in Randomized Smoothing for Audio Classification](https://mlsanity.com/paper/2606.04210/) (2026)
- [The Geometry of Randomized Smoothing on Feasible Sets](https://mlsanity.com/paper/2609.39497/) (2026)

## Abstract (arXiv)

Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers. While randomized smoothing typically yields robust ℓ2-ball certificates, recent research has generalized provable robustness to different norm balls as well as anisotropic regions. This work considers a classifier architecture that first projects onto a low-dimensional approximation of the data manifold and then applies a standard classifier. By performing randomized smoothing in the low-dimensional projected space, we characterize the certified region of our smoothed composite classifier back in the high-dimensional input space and prove a tractable lower bound on its volume. We show experimentally on CIFAR-10 and SVHN that classifiers without the initial projection are vulnerable to perturbations that are normal to the data manifold and yet are captured by the certified regions of our method. We compare the volume of our certified regions against various baselines and show that our method improves on the state-of-the-art by many orders of magnitude.