mlsanityData to 14 Oct 2026

fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systems

arXiv 2205.13807 ↗First posted 27 May 2022cs.LG cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

Recently, Deep Neural Networks (DNNs) have achieved remarkable performances in many applications, while several studies have enhanced their vulnerabilities to malicious attacks. In this paper, we emulate the effects of natural weather conditions to introduce plausible perturbations that mislead the DNNs. By observing the effects of such atmospheric perturbations on the camera lenses, we model the patterns to create different masks that fake the effects of rain, snow, and hail. Even though the perturbations introduced by our attacks are visible, their presence remains unnoticed due to their association with natural events, which can be especially catastrophic for fully-autonomous and unmanned vehicles. We test our proposed fakeWeather attacks on multiple Convolutional Neural Network and Capsule Network models, and report noticeable accuracy drops in the presence of such adversarial perturbations. Our work introduces a new security threat for DNNs, which is especially severe for safety-critical applications and autonomous systems.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

27 of 41 references.

References · 27

  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. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  8. 2016Universal adversarial perturbationscited by 784
  9. 2017Dynamic Routing Between Capsulescited by 689
  10. 2017One pixel attack for fooling deep neural networkscited by 582
  11. 2017Adversarial Patchcited by 517
  12. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
15 more
  1. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  2. 2019A Survey of Deep Learning-based Object Detectioncited by 106
  3. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 106
  4. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  5. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 41
  6. 2018Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networkscited by 38
  7. 2020Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Aheadcited by 34
  8. 2020CD-UAP: Class Discriminative Universal Adversarial Perturbationcited by 27
  9. 2021Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Frameworkcited by 17
  10. 2019Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristicscited by 14
  11. 2021Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directionscited by 9
  12. 2019CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networkscited by 8
  13. 2019Perceptual Quality-preserving Black-Box Attack against Deep Learning Image Classifierscited by 8
  14. 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
  15. 2021You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queriescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 0; 2025: 1; 2026: 2.

8 papers.

  1. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  2. 2023Distracting Downpour: Adversarial Weather Attacks for Motion Estimationcited by 15
  3. 2022Attacking Motion Estimation with Adversarial Snowcited by 9
  4. 2023AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systemscited by 8
  5. 2023RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attackscited by 1
  6. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  7. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1
  8. 2026Discovering Natural Transformation Vulnerabilities in Black-Box Vision Modelscited by 0