mlsanityData to 7 Oct 2026

Imperceptible Adversarial Attack via Invertible Neural Networks

arXiv 2211.15030 ↗First posted 28 Nov 2022cs.CV eess.IVcited by 12

Not on the map. Why?

Abstract (arXiv)

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of adversarial examples, conventional adversarial attacks still generate traceable adversarial perturbations. In this paper, we introduce a novel Adversarial Attack via Invertible Neural Networks (AdvINN) method to produce robust and imperceptible adversarial examples. Specifically, AdvINN fully takes advantage of the information preservation property of Invertible Neural Networks and thereby generates adversarial examples by simultaneously adding class-specific semantic information of the target class and dropping discriminant information of the original class. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that the proposed AdvINN method can produce less imperceptible adversarial images than the state-of-the-art methods and AdvINN yields more robust adversarial examples with high confidence compared to other adversarial attacks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 48 of its 58 references that are in the map. First posted on arXiv 28 Nov 2022.

Builds on

48 of 58 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Natural Adversarial Examplescited by 1,401
36 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  3. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  4. 2016Adversarial Machine Learning at Scalecited by 934
  5. 2016Universal adversarial perturbationscited by 774
  6. 2017Countering Adversarial Images using Input Transformationscited by 517
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  8. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  9. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  10. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  11. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
  12. 2017Generative Adversarial Perturbationscited by 153
  13. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  14. 2018i-RevNet: Deep Invertible Networkscited by 137
  15. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  16. 2020Invertible Image Rescalingcited by 92
  17. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  18. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 76
  19. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  20. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 72
  21. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
  22. 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
  23. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  24. 2017Art of singular vectors and universal adversarial perturbationscited by 49
  25. 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
  26. 2018Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networkscited by 38
  27. 2020AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flowscited by 35
  28. 2021WINNet: Wavelet-inspired Invertible Network for Image Denoisingcited by 33
  29. 2020Double Targeted Universal Adversarial Perturbationscited by 23
  30. 2022Invertible Rescaling Network and Its Extensionscited by 15
  31. 2021IICNet: A Generic Framework for Reversible Image Conversioncited by 13
  32. 2021Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscalingcited by 6
  33. 2021LINN: Lifting Inspired Invertible Neural Network for Image Denoisingcited by 6
  34. 2021A Compact Neural Network-based Algorithm for Robust Image Watermarkingcited by 6
  35. 2022Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Networkcited by 4
  36. 2022DURRNet: Deep Unfolded Single Image Reflection Removal Networkcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 6; 2026: 2.

12 papers.

  1. 2024Semantic Deep Hiding for Robust Unlearnable Examplescited by 13
  2. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attackscited by 7
  3. 2023Adversarial Image Generation by Spatial Transformation in Perceptual Colorspacescited by 3
  4. 2025AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perceptioncited by 3
  5. 2025FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Modelscited by 3
  6. 2024SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural Networkscited by 1
  7. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  8. 2024PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attackscited by 0
  9. 2025SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Networkcited by 0
  10. 2025Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systemscited by 0
  11. 2026AMIF: Authorizable Medical Image Fusion Model with Built-in Authenticationcited by 0
  12. 2026Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Drivingcited by 0