mlsanityData to 14 Oct 2026

Poisoning the Search Space in Neural Architecture Search

arXiv 2106.14406 ↗First posted 28 Jun 2021cs.LG cs.CR cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning has proven to be a highly effective problem-solving tool for object detection and image segmentation across various domains such as healthcare and autonomous driving. At the heart of this performance lies neural architecture design which relies heavily on domain knowledge and prior experience on the researchers' behalf. More recently, this process of finding the most optimal architectures, given an initial search space of possible operations, was automated by Neural Architecture Search (NAS). In this paper, we evaluate the robustness of one such algorithm known as Efficient NAS (ENAS) against data agnostic poisoning attacks on the original search space with carefully designed ineffective operations. By evaluating algorithm performance on the CIFAR-10 dataset, we empirically demonstrate how our novel search space poisoning (SSP) approach and multiple-instance poisoning attacks exploit design flaws in the ENAS controller to result in inflated prediction error rates for child networks. Our results provide insights into the challenges to surmount in using NAS for more adversarially robust architecture search.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 28 Jun 2021.

Builds on

18 of 27 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  4. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  5. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  6. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  7. 2017Progressive Neural Architecture Searchcited by 487
  8. 2018Adversarial Attacks and Defences: A Surveycited by 259
  9. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
  10. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  11. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  12. 2016Deep Learning for Identifying Metastatic Breast Cancercited by 93
6 more
  1. 2018Is feature selection secure against training data poisoning?cited by 93
  2. 2019When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attackscited by 87
  3. 2019A Survey on Neural Architecture Searchcited by 71
  4. 2019Best Practices for Scientific Research on Neural Architecture Searchcited by 54
  5. 2017Generative Poisoning Attack Method Against Neural Networkscited by 52
  6. 2019Evolving Robust Neural Architectures to Defend from Adversarial Attackscited by 13

Built on by

Not cited yet.