mlsanityData to 14 Oct 2026

Towards Deep Neural Network Architectures Robust to Adversarial Examples

arXiv 1412.5068 ↗First posted 11 Dec 2014cs.LG cs.CV cs.NEcited by 146

Not on the map. Why?

Abstract (arXiv)

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are often imperceptible, but can result in 100% mis-classification for a state of the art DNN. We study the structure of adversarial examples and explore network topology, pre-processing and training strategies to improve the robustness of DNNs. We perform various experiments to assess the removability of adversarial examples by corrupting with additional noise and pre-processing with denoising autoencoders (DAEs). We find that DAEs can remove substantial amounts of the adversarial noise. How- ever, when stacking the DAE with the original DNN, the resulting network can again be attacked by new adversarial examples with even smaller distortion. As a solution, we propose Deep Contractive Network, a model with a new end-to-end training procedure that includes a smoothness penalty inspired by the contractive autoencoder (CAE). This increases the network robustness to adversarial examples, without a significant performance penalty.

Key facts. Cited by 146 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 47; 2022: 35; 2023: 30; 2024: 19; 2025: 12; 2026: 3.

146 papers.

Sort:

By area:

  1. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,095
  2. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  3. 2021Towards Causal Representation Learningcited by 209
  4. 2021Trustworthy AI: From Principles to Practicescited by 207
  5. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  6. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  7. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  8. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  9. 2022Robust Semantic Communications with Masked VQ-VAE Enabled Codebookcited by 56
  10. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  11. 2022Shape-invariant 3D Adversarial Point Cloudscited by 50
  12. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
38 more
  1. 2021Online Adversarial Purification based on Self-Supervisioncited by 46
  2. 2021Optical Adversarial Attackcited by 43
  3. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 36
  4. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  5. 2024Immunization against harmful fine-tuning attackscited by 35
  6. 2021On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Modelscited by 31
  7. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 30
  8. 2023Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivativescited by 30
  9. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  10. 2024Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspectivecited by 28
  11. 2025reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputscited by 25
  12. 2023Defending against Adversarial Audio via Diffusion Modelcited by 23
  13. 2021Generative Dynamic Patch Attackcited by 19
  14. 2024Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Maskingcited by 19
  15. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18
  16. 2021On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attackscited by 17
  17. 2024Towards Adversarially Robust Dataset Distillation by Curvature Regularizationcited by 17
  18. 2021Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Votingcited by 16
  19. 2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
  20. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  21. 2021Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attackcited by 15
  22. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  23. 2024Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Losscited by 14
  24. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 14
  25. 2022An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networkscited by 11
  26. 2021DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classificationcited by 10
  27. 2022PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognitioncited by 10
  28. 2023Data Augmentation in Training CNNs: Injecting Noise to Imagescited by 10
  29. 2021Revisiting Model's Uncertainty and Confidences for Adversarial Example Detectioncited by 9
  30. 2021Morphence: Moving Target Defense Against Adversarial Examplescited by 9
  31. 2021Fast Gradient Non-sign Methodscited by 9
  32. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  33. 2022Threat Assessment in Machine Learning based Systemscited by 9
  34. 2021Adversarial Attacks and Defenses in Physiological Computing: A Systematic Reviewcited by 8
  35. 2023Understanding Noise-Augmented Training for Randomized Smoothingcited by 7
  36. 2021Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practicecited by 6
  37. 2021Towards Adversarial Patch Analysis and Certified Defense against Crowd Countingcited by 6
  38. 2022A Tale of Two Models: Constructing Evasive Attacks on Edge Modelscited by 6

50 most cited of 146 All 146 (JSON)