mlsanityData to 14 Oct 2026

Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond

arXiv 2203.16931 ↗First posted 31 Mar 2022cs.CV cs.CRcited by 48

Not on the map. Why?

Abstract (arXiv)

Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many computer vision algorithms to function properly. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks. Our study shows that, when the image/video is highly degraded, rain removal methods are more vulnerable to the adversarial attacks as small distortions/perturbations become less noticeable or detectable. In this paper, we first present a comprehensive empirical evaluation of various methods at different levels of attacks and with various losses/targets to generate the perturbations from the perspective of human perception and machine analysis tasks. A systematic evaluation of key modules in existing methods is performed in terms of their robustness against adversarial attacks. From the insights of our analysis, we construct a more robust deraining method by integrating these effective modules. Finally, we examine various types of adversarial attacks that are specific to deraining problems and their effects on both human and machine vision tasks, including 1) rain region attacks, adding perturbations only in the rain regions to make the perturbations in the attacked rain images less visible; 2) object-sensitive attacks, adding perturbations only in regions near the given objects. Code is available at https://github.com/yuyi-sd/Robust_Rain_Removal.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

34 of 53 references.

References · 34

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2021Multi-Stage Progressive Image Restorationcited by 816
  12. 2019Selective Kernel Networkscited by 403
22 more
  1. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  2. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  3. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 272
  4. 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 260
  5. 2018Density-aware Single Image De-raining using a Multi-stream Dense Networkcited by 248
  6. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  7. 2019Spatial Attentive Single-Image Deraining with a High Quality Real Rain Datasetcited by 192
  8. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  9. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  10. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  11. 2020A Model-driven Deep Neural Network for Single Image Rain Removalcited by 125
  12. 2019Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Rainingcited by 117
  13. 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 65
  14. 2018Lightweight Pyramid Networks for Image Derainingcited by 64
  15. 2020Syn2Real Transfer Learning for Image Deraining using Gaussian Processescited by 62
  16. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  17. 2019Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attackscited by 37
  18. 2020Global Context Networkscited by 35
  19. 2018Non-locally Enhanced Encoder-Decoder Network for Single Image De-rainingcited by 33
  20. 2021AdvHaze: Adversarial Haze Attackcited by 31
  21. 2020Conditional Variational Image Derainingcited by 22
  22. 2017Single Image Deraining using Scale-Aware Multi-Stage Recurrent Networkcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 15; 2024: 17; 2025: 7; 2026: 4.

48 papers.

Sort:

By area:

  1. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 103
  2. 2023Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Triggercited by 40
  3. 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
  4. 2023Towards Unified Deep Image Deraining: A Survey and A New Benchmarkcited by 34
  5. 2023PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentationcited by 26
  6. 2024Transferable Adversarial Attacks on SAM and Its Downstream Modelscited by 21
  7. 2024Purify Unlearnable Examples via Rate-Constrained Variational Autoencoderscited by 18
  8. 2022Magic ELF: Image Deraining Meets Association Learning and Transformercited by 17
  9. 2023Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptationcited by 16
  10. 2023Temporal Coherent Test-Time Optimization for Robust Video Classificationcited by 15
  11. 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothingcited by 15
  12. 2022Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Qualitycited by 13
36 more
  1. 2024Semantic Deep Hiding for Robust Unlearnable Examplescited by 13
  2. 2025When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Modelscited by 13
  3. 2024Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Triggercited by 12
  4. 2023On the unreasonable vulnerability of transformers for image restoration -- and an easy fixcited by 11
  5. 2024Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Priorcited by 11
  6. 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learningcited by 11
  7. 2024Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attackscited by 10
  8. 2025Towards Model Resistant to Transferable Adversarial Examples via Trigger Activationcited by 10
  9. 2024Unlearnable Examples Detection via Iterative Filteringcited by 9
  10. 2025From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledgecited by 9
  11. 2025CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabularycited by 8
  12. 2024Towards Physical World Backdoor Attacks against Skeleton Action Recognitioncited by 7
  13. 2022Two-branch Multi-scale Deep Neural Network for Generalized Document Recapture Attack Detectioncited by 6
  14. 2023Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Drivingcited by 6
  15. 2024Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attackscited by 6
  16. 2026Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networkscited by 5
  17. 2026AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Modelscited by 5
  18. 2023Fooling the Image Dehazing Models by First Order Gradientcited by 3
  19. 2024WaveMo: Learning Wavefront Modulations to See Through Scatteringcited by 3
  20. 2024Adversarial Attacks on Hyperbolic Networkscited by 3
  21. 2024CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detectioncited by 2
  22. 2023Unsupervised Deep Digital Staining For Microscopic Cell Images Via Knowledge Distillationcited by 1
  23. 2024textrmA^textrm2RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusioncited by 1
  24. 2025Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Datasetcited by 1
  25. 2025Cross Paradigm Representation and Alignment Transformer for Image Derainingcited by 1
  26. 2022Asymmetric Dual-Decoder U-Net for Joint Rain and Haze Removalcited by 0
  27. 2023Learning Image Deraining Transformer Network with Dynamic Dual Self-Attentioncited by 0
  28. 2023When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-k Multi-Label Learningcited by 0
  29. 2023CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perceptioncited by 0
  30. 2023Dynamic Association Learning of Self-Attention and Convolution in Image Restorationcited by 0
  31. 2023Trainwreck: A damaging adversarial attack on image classifierscited by 0
  32. 2024Adversarial Purification and Fine-tuning for Robust UDC Image Restorationcited by 0
  33. 2024Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Modelscited by 0
  34. 2024Unsupervised Network for Single Image Raindrop Removalcited by 0
  35. 2026StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Liftingcited by 0
  36. 2026Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditionscited by 0