mlsanityData to 14 Oct 2026

AdvDrop: Adversarial Attack to DNNs by Dropping Information

arXiv 2108.09034 ↗First posted 20 Aug 2021cs.CV cs.CR cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects (visual objects with lost information) is still a challenge. In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? Towards this end, we propose a novel adversarial attack, named textitAdvDrop, which crafts adversarial examples by dropping existing information of images. Previously, most adversarial attacks add extra disturbing information on clean images explicitly. Opposite to previous works, our proposed work explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible details to craft adversarial examples. We demonstrate the effectiveness of textitAdvDrop by extensive experiments, and show that this new type of adversarial examples is more difficult to be defended by current defense systems.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

35 of 52 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Adversarial examples in the physical worldcited by 1,769
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  11. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  12. 2017Countering Adversarial Images using Input Transformationscited by 520
23 more
  1. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  2. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  3. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 219
  4. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  5. 2017Generating Natural Adversarial Examplescited by 183
  6. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 175
  7. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  8. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 152
  9. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  10. 2017Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networkscited by 92
  11. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  12. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 87
  13. 2018Semantic Adversarial Examplescited by 86
  14. 2018Low Frequency Adversarial Perturbationcited by 80
  15. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 76
  16. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  17. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  18. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 73
  19. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  20. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  21. 2019On the Effectiveness of Low Frequency Perturbationscited by 56
  22. 2019Physical Adversarial Textures that Fool Visual Object Trackingcited by 31
  23. 2019SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbationscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 12; 2023: 15; 2024: 15; 2025: 10; 2026: 3.

56 papers.

Sort:

By area:

  1. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 130
  2. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  3. 2022Enhance the Visual Representation via Discrete Adversarial Trainingcited by 23
  4. 2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
  5. 2022Boosting 3D Adversarial Attacks with Attacking On Frequencycited by 18
  6. 2024Unified Physical-Digital Face Attack Detectioncited by 17
  7. 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothingcited by 15
  8. 2023Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averagingcited by 14
  9. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  10. 2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
  11. 2023Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical Worldcited by 11
  12. 2022LPF-Defense: 3D Adversarial Defense based on Frequency Analysiscited by 10
38 more
  1. 2023Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical Worldcited by 10
  2. 2022Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspectivecited by 8
  3. 2023Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworkscited by 8
  4. 2024Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Cluescited by 8
  5. 2024FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attackscited by 8
  6. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
  7. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attackscited by 8
  8. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 8
  9. 2024GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative modelcited by 7
  10. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  11. 2022Adversarial Neon Beam: A Light-based Physical Attack to DNNscited by 6
  12. 2023Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentationcited by 6
  13. 2025SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generationcited by 6
  14. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  15. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  16. 2023Adversarial Robust Memory-Based Continual Learnercited by 5
  17. 2024Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attackscited by 5
  18. 2024AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Modelscited by 5
  19. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  20. 2022RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compressioncited by 4
  21. 2023Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical worldcited by 4
  22. 2023Adversarial Image Generation by Spatial Transformation in Perceptual Colorspacescited by 3
  23. 2024Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferabilitycited by 3
  24. 2025AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perceptioncited by 3
  25. 2024STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenariocited by 2
  26. 2025Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognitioncited by 2
  27. 2025DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examplescited by 2
  28. 2022Adversarial Color Projection: A Projector-based Physical Attack to DNNscited by 1
  29. 2023Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalizationcited by 1
  30. 2023Advancing Adversarial Training by Injecting Booster Signalcited by 1
  31. 2023Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithmcited by 1
  32. 2023SSTA: Salient Spatially Transformed Attackcited by 1
  33. 2024SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural Networkscited by 1
  34. 2024Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Gridcited by 1
  35. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  36. 2025T-MLA: A targeted multiscale log-exponential attack framework for neural image compressioncited by 1
  37. 2026Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticitycited by 1
  38. 2022Gradient Concealment: Free Lunch for Defending Adversarial Attackscited by 0

50 most cited of 56 All 56 (JSON)