mlsanityData to 7 Oct 2026

ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples

arXiv 1811.12673 ↗First posted 30 Nov 2018cs.CVcited by 104

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: ComDefend. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is used to reconstruct the original image with high quality. In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier. Our method is a pre-processing module, and does not modify the classifier's structure during the whole process. Therefore, it can be combined with other model-specific defense models to jointly improve the classifier's robustness. A series of experiments conducted on MNIST, CIFAR10 and ImageNet show that the proposed method outperforms the state-of-the-art defense methods, and is consistently effective to protect classifiers against adversarial attacks.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 20; 2023: 25; 2024: 13; 2025: 17; 2026: 5.

104 papers.

Sort:

By area:

  1. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
  4. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  5. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  6. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 77
  7. 2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
  8. 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
  9. 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignmentcited by 42
  10. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  11. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  12. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
38 more
  1. 2023Improving the Transferability of Adversarial Samples by Path-Augmented Methodcited by 36
  2. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  3. 2022Transferable Adversarial Attack based on Integrated Gradientscited by 35
  4. 2022Prior-Guided Adversarial Initialization for Fast Adversarial Trainingcited by 34
  5. 2023Improving Fast Adversarial Training with Prior-Guided Knowledgecited by 34
  6. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  7. 2022Boosting the Transferability of Adversarial Attacks with Global Momentum Initializationcited by 29
  8. 2025ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichmentcited by 27
  9. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  10. 2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
  11. 2023Improving Adversarial Transferability by Stable Diffusioncited by 22
  12. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  13. 2022Defensive Patches for Robust Recognition in the Physical Worldcited by 20
  14. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  15. 2022StyleFool: Fooling Video Classification Systems via Style Transfercited by 18
  16. 2021Attack to Fool and Explain Deep Networkscited by 17
  17. 2022Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processingcited by 16
  18. 2024Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Networkcited by 15
  19. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  20. 2023Improving the Transferability of Adversarial Examples with Arbitrary Style Transfercited by 13
  21. 2023Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomnesscited by 13
  22. 2021Adversarial example generation with AdaBelief Optimizer and Crop Invariancecited by 12
  23. 2021Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attackscited by 11
  24. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  25. 2024Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Modelscited by 11
  26. 2025Towards Model Resistant to Transferable Adversarial Examples via Trigger Activationcited by 10
  27. 2021MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attackcited by 9
  28. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  29. 2023Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillationcited by 7
  30. 2023Adversarial Attack Based on Prediction-Correctioncited by 7
  31. 2021Direction-Aggregated Attack for Transferable Adversarial Examplescited by 6
  32. 2021Adaptive Perturbation for Adversarial Attackcited by 6
  33. 2023ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patchescited by 6
  34. 2023LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfercited by 6
  35. 2025Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Modelscited by 6
  36. 2021An Effective and Robust Detector for Logo Detectioncited by 5
  37. 2021All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelinescited by 5
  38. 2022Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attackscited by 5

50 most cited of 104 All 104 (JSON)