mlsanityData to 7 Oct 2026

Robust and Accurate -- Compositional Architectures for Randomized Smoothing

arXiv 2204.00487 ↗First posted 1 Apr 2022cs.LG cs.AI cs.CRcited by 12

Not on the map. Why?

Abstract (arXiv)

Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting their real-world utility. To address this limitation, we propose a compositional architecture, ACES, which certifiably decides on a per-sample basis whether to use a smoothed model yielding predictions with guarantees or a more accurate standard model without guarantees. This, in contrast to prior approaches, enables both high standard accuracies and significant provable robustness. On challenging tasks such as ImageNet, we obtain, e.g., 80.0% natural accuracy and 28.2% certifiable accuracy against ℓ2 perturbations with r=1.0. We release our code and models at https://github.com/eth-sri/aces.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

24 of 41 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2018Robustness May Be at Odds with Accuracycited by 873
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
12 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  2. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  3. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  4. 2019Adversarial Examples Improve Image Recognitioncited by 283
  5. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  6. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
  7. 2019Adversarial Training Can Hurt Generalizationcited by 131
  8. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  9. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  10. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  11. 2020Data-Dependent Randomized Smoothingcited by 37
  12. 2021Intriguing Properties of Input-dependent Randomized Smoothingcited by 24

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 4.

12 papers.

  1. 2022(Certified!!) Adversarial Robustness for Free!cited by 130
  2. 2023TAPS: Connecting Certified and Adversarial Trainingcited by 11
  3. 2023Hierarchical Randomized Smoothingcited by 9
  4. 2023Multi-scale Diffusion Denoised Smoothingcited by 9
  5. 2022(De-)Randomized Smoothing for Decision Stump Ensemblescited by 5
  6. 2022Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classescited by 4
  7. 2024SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothingcited by 4
  8. 2023Rethinking Randomized Smoothing from the Perspective of Scalabilitycited by 3
  9. 2024Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustnesscited by 2
  10. 2023Exploring Transferability for Randomized Smoothingcited by 1
  11. 2024Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothingcited by 1
  12. 2024Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustnesscited by 0