mlsanityData to 14 Oct 2026

Potential Auto-driving Threat: Universal Rain-removal Attack

arXiv 2211.09959 ↗First posted 18 Nov 2022cs.CV cs.AI eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

The problem of robustness in adverse weather conditions is considered a significant challenge for computer vision algorithms in the applicants of autonomous driving. Image rain removal algorithms are a general solution to this problem. They find a deep connection between raindrops/rain-streaks and images by mining the hidden features and restoring information about the rain-free environment based on the powerful representation capabilities of neural networks. However, previous research has focused on architecture innovations and has yet to consider the vulnerability issues that already exist in neural networks. This research gap hints at a potential security threat geared toward the intelligent perception of autonomous driving in the rain. In this paper, we propose a universal rain-removal attack (URA) on the vulnerability of image rain-removal algorithms by generating a non-additive spatial perturbation that significantly reduces the similarity and image quality of scene restoration. Notably, this perturbation is difficult to recognise by humans and is also the same for different target images. Thus, URA could be considered a critical tool for the vulnerability detection of image rain-removal algorithms. It also could be developed as a real-world artificial intelligence attack method. Experimental results show that URA can reduce the scene repair capability by 39.5% and the image generation quality by 26.4%, targeting the state-of-the-art (SOTA) single-image rain-removal algorithms currently available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 58 references that are in the map. First posted on arXiv 18 Nov 2022.

Builds on

22 of 58 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2016Universal adversarial perturbationscited by 784
  6. 2017Generative Adversarial Networks: An Overviewcited by 590
  7. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  8. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  9. 2018Density-aware Single Image De-raining using a Multi-stream Dense Networkcited by 248
  10. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  11. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  12. 2018Spatially Transformed Adversarial Examplescited by 195
10 more
  1. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  2. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  3. 2017Generative Adversarial Perturbationscited by 153
  4. 2016Clearing the Skies: A deep network architecture for single-image rain removalcited by 136
  5. 2017NAG: Network for Adversary Generationcited by 51
  6. 2019Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forwardcited by 33
  7. 2021Robust Representation Learning with Feedback for Single Image Derainingcited by 32
  8. 2015Manitest: Are classifiers really invariant?cited by 27
  9. 2017Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challengescited by 24
  10. 2018Residual-Guide Feature Fusion Network for Single Image Derainingcited by 15

Built on by

Not cited yet.