mlsanityData to 14 Oct 2026

Regularizing deep networks using efficient layerwise adversarial training

arXiv 1705.07819 ↗First posted 22 May 2017cs.CV cs.LG stat.MLcited by 24

Not on the map. Why?

Abstract (arXiv)

Adversarial training has been shown to regularize deep neural networks in addition to increasing their robustness to adversarial examples. However, its impact on very deep state of the art networks has not been fully investigated. In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations as a regularizer during training. We use these perturbations to train very deep models such as ResNets and show improvement in performance both on adversarial and original test data. Our experiments highlight the benefits of perturbing intermediate layer activations compared to perturbing only the inputs. The results on CIFAR-10 and CIFAR-100 datasets show the merits of the proposed adversarial training approach. Additional results on WideResNets show that our approach provides significant improvement in classification accuracy for a given base model, outperforming dropout and other base models of larger size.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 2; 2023: 4; 2024: 9; 2025: 3.

24 papers.

Sort:

By area:

  1. 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 173
  2. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  3. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 88
  4. 2025Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilitiescited by 39
  5. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  6. 2021Reliably fast adversarial training via latent adversarial perturbationcited by 29
  7. 2024Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspectivecited by 28
  8. 2021CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selectioncited by 21
  9. 2023Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attackcited by 6
  10. 2024Adversarial Training: A Surveycited by 6
  11. 2025Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustnesscited by 5
  12. 2024Module-wise Adaptive Adversarial Training for End-to-end Autonomous Drivingcited by 4
12 more
  1. 2023Adversarial Robustness in Unsupervised Machine Learning: A Systematic Reviewcited by 3
  2. 2024Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructurescited by 3
  3. 2022Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) frameworkcited by 2
  4. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examplescited by 2
  5. 2021Robust Regularization with Adversarial Labelling of Perturbed Samplescited by 1
  6. 2021Improving Adversarial Robustness for Free with Snapshot Ensemblecited by 1
  7. 2021Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackerscited by 1
  8. 2023Lateralized Learning for Multi-Class Visual Classification Taskscited by 1
  9. 2022Defending Adversarial Examples by Negative Correlation Ensemblecited by 0
  10. 2023Adversarial Defenses via Vector Quantizationcited by 0
  11. 2024Natias: Neuron Attribution based Transferable Image Adversarial Steganographycited by 0
  12. 2025MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examplescited by 0