mlsanityData to 14 Oct 2026

Adversarial Defense by Stratified Convolutional Sparse Coding

arXiv 1812.00037 ↗First posted 30 Nov 2018cs.CV cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of dataset size. Based on convolutional sparse coding, we construct a stratified low-dimensional quasi-natural image space that faithfully approximates the natural image space while also removing adversarial perturbations. We introduce a novel Sparse Transformation Layer (STL) in between the input image and the first layer of the neural network to efficiently project images into our quasi-natural image space. Our experiments show state-of-the-art performance of our method compared to other attack-agnostic adversarial defense methods in various adversarial settings.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 4; 2023: 5; 2024: 7; 2025: 3; 2026: 1.

31 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
  3. 2021The Dimpled Manifold Model of Adversarial Examples in Machine Learningcited by 41
  4. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 40
  5. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Modelscited by 38
  6. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 34
  7. 2021Can audio-visual integration strengthen robustness under multimodal attacks?cited by 23
  8. 2021Attack to Fool and Explain Deep Networkscited by 17
  9. 2021AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningcited by 10
  10. 2021RAILS: A Robust Adversarial Immune-inspired Learning Systemcited by 8
  11. 2023Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detectioncited by 8
  12. 2024Improving Robustness to Model Inversion Attacks via Sparse Coding Architecturescited by 8
19 more
  1. 2022InfoAT: Improving Adversarial Training Using the Information Bottleneck Principlecited by 7
  2. 2022Perturbation Inactivation Based Adversarial Defense for Face Recognitioncited by 5
  3. 2023CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Spacecited by 4
  4. 2021Brain Image Synthesis with Unsupervised Multivariate Canonical CSCℓ4Netcited by 3
  5. 2021Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustnesscited by 2
  6. 2022Data-free Defense of Black Box Models Against Adversarial Attackscited by 2
  7. 2023A Random-patch based Defense Strategy Against Physical Attacks for Face Recognition Systemscited by 2
  8. 2024VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noisecited by 2
  9. 2024Artificial Immune System of Secure Face Recognition Against Adversarial Attackscited by 2
  10. 2025An Investigation of Visual Foundation Models Robustnesscited by 2
  11. 2021Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purificationcited by 1
  12. 2023IRAD: Implicit Representation-driven Image Resampling against Adversarial Attackscited by 1
  13. 2024ZeroPur: Succinct Training-Free Adversarial Purificationcited by 1
  14. 2024OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attackcited by 1
  15. 2021Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attackscited by 0
  16. 2021Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influencecited by 0
  17. 2025On Transfer-based Universal Attacks in Pure Black-box Settingcited by 0
  18. 2025VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systemscited by 0
  19. 2026Brain Tumor Classifiers Under Attack: Robustness of ResNet Variants Against Transferable FGSM and PGD Attackscited by 0