mlsanityData to 7 Oct 2026

Deep Defense: Training DNNs with Improved Adversarial Robustness

arXiv 1803.00404 ↗First posted 23 Feb 2018cs.CV cs.LG cs.NEcited by 41

Not on the map. Why?

Abstract (arXiv)

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating imperceptibly perturbed image inputs (a.k.a., adversarial examples) to fool well-trained DNN classifiers into making arbitrary predictions. To address this problem, we propose a training recipe named "deep defense". Our core idea is to integrate an adversarial perturbation-based regularizer into the classification objective, such that the obtained models learn to resist potential attacks, directly and precisely. The whole optimization problem is solved just like training a recursive network. Experimental results demonstrate that our method outperforms training with adversarial/Parseval regularizations by large margins on various datasets (including MNIST, CIFAR-10 and ImageNet) and different DNN architectures. Code and models for reproducing our results are available at https://github.com/ZiangYan/deepdefense.pytorch

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 10; 2023: 3; 2024: 1; 2025: 5; 2026: 3.

41 papers.

Sort:

By area:

  1. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  2. 2021A Comprehensive Evaluation Framework for Deep Model Robustnesscited by 41
  3. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  4. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
  5. 2021Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustnesscited by 20
  6. 2023Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularizationcited by 19
  7. 2022Pruning Adversarially Robust Neural Networks without Adversarial Examplescited by 12
  8. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  9. 2021AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learningcited by 9
  10. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  11. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  12. 2021Perceptually Constrained Adversarial Attackscited by 7
29 more
  1. 2021Recent Advances in Large Margin Learningcited by 7
  2. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  3. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  4. 2024SafeLight: Enhancing Security in Optical Convolutional Neural Network Acceleratorscited by 4
  5. 2021Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximationcited by 3
  6. 2021Adaptive Feature Alignment for Adversarial Trainingcited by 3
  7. 2021Clustering Effect of (Linearized) Adversarial Robust Modelscited by 3
  8. 2022An Eye for an Eye: Defending against Gradient-based Attacks with Gradientscited by 2
  9. 2022Adversarial Attack and Defense for Non-Parametric Two-Sample Testscited by 2
  10. 2022Deadwooding: Robust Global Pruning for Deep Neural Networkscited by 2
  11. 2022SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learningcited by 2
  12. 2023RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillationcited by 2
  13. 2021Robust Upper Bounds for Adversarial Trainingcited by 1
  14. 2022Two Heads are Better than One: Robust Learning Meets Multi-branch Modelscited by 1
  15. 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approachcited by 1
  16. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  17. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  18. 2021Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbationscited by 0
  19. 2021MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysiscited by 0
  20. 2021On Procedural Adversarial Noise Attack And Defensecited by 0
  21. 2021Holistic Deep Learningcited by 0
  22. 2022An Effective Fusion Method to Enhance the Robustness of CNNcited by 0
  23. 2022Stable and Efficient Adversarial Training through Local Linearizationcited by 0
  24. 2023Dendritic Integration Based Quadratic Neural Networks Outperform Traditional Aritificial Onescited by 0
  25. 2025Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustnesscited by 0
  26. 2025Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Eracited by 0
  27. 2026PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devicescited by 0
  28. 2026Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbationscited by 0
  29. 2026Theory of Continual Learning Against Data Poisoning Attackscited by 0