mlsanityData to 7 Oct 2026

Robust Neural Architecture Search

arXiv 2304.02845 ↗First posted 6 Apr 2023cs.LG cs.AI cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to enhance the robustness of NAS-generated models, however, they neglected the nature accuracy of NAS-generated models. In our paper, we propose a novel NAS method, Robust Neural Architecture Search (RNAS). To design a regularization term to balance accuracy and robustness, RNAS generates architectures with both high accuracy and good robustness. To reduce search cost, we further propose to use noise examples instead adversarial examples as input to search architectures. Extensive experiments show that RNAS achieves state-of-the-art (SOTA) performance on both image classification and adversarial attacks, which illustrates the proposed RNAS achieves a good tradeoff between robustness and accuracy.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 29 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

28 of 29 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  8. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  9. 2018Robustness May Be at Odds with Accuracycited by 873
  10. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  11. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  12. 2019Adversarial Training for Free!cited by 638
16 more
  1. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  2. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  3. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  4. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 258
  5. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  6. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  7. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 176
  8. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  9. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  10. 2019When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attackscited by 87
  11. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  12. 2020Adversarially Robust Neural Architecturescited by 22
  13. 2021Neural Architecture Dilation for Adversarial Robustnesscited by 13
  14. 2021On the Security Risks of AutoMLcited by 7
  15. 2023Improving Differentiable Architecture Search via Self-Distillationcited by 6
  16. 2023Operation-level Progressive Differentiable Architecture Searchcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 2; 2026: 1.

5 papers.

  1. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  2. 2024FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustnesscited by 5
  3. 2025ProARD: progressive adversarial robustness distillation: provide wide range of robust studentscited by 0
  4. 2025Neural Architecture Search with Mixed Bio-inspired Learning Rulescited by 0
  5. 2026HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Searchcited by 0