mlsanityData to 7 Oct 2026

Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input

arXiv 2203.09123 ↗First posted 17 Mar 2022cs.CV cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate, adversarial examples should avoid overfitting to the source model, and image augmentation is one of the primary approaches for this. However, prior works utilize simple image transformations such as resizing, which limits input diversity. To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class. Our motivation comes from the humans' superior perception of an image printed on a 3D object. If the image is clear enough, humans can recognize the image content in a variety of viewing conditions. Likewise, if an adversarial example looks like the target class to the model, the model should also classify the rendered image of the 3D object as the target class. The ODI method effectively diversifies the input by leveraging an ensemble of multiple source objects and randomizing viewing conditions. In our experimental results on the ImageNet-Compatible dataset, this method boosts the average targeted attack success rate from 28.3% to 47.0% compared to the state-of-the-art methods. We also demonstrate the applicability of the ODI method to adversarial examples on the face verification task and its superior performance improvement. Our code is available at https://github.com/dreamflake/ODI.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

34 of 47 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
22 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  3. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  6. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  7. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  8. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  9. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  10. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  11. 2019GhostNet: More Features from Cheap Operationscited by 410
  12. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  13. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  14. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  15. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  16. 2020Differentiable Rendering: A Surveycited by 123
  17. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  18. 2018Adversarial Attacks and Defences Competitioncited by 96
  19. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  20. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  21. 2019Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reductioncited by 47
  22. 2021Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fittingcited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 23; 2024: 13; 2025: 7; 2026: 2.

49 papers.

Sort:

By area:

  1. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
  2. 2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
  3. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  4. 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
  5. 2025Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignmentcited by 42
  6. 2023SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentationcited by 39
  7. 2023OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimizationcited by 36
  8. 2022Enhancing the Self-Universality for Transferable Targeted Attackscited by 30
  9. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  10. 2024Transferable Adversarial Attacks on SAM and Its Downstream Modelscited by 20
  11. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  12. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
37 more
  1. 2023Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibrationcited by 18
  2. 2023Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixupcited by 17
  3. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
  4. 2023Improving the Transferability of Adversarial Examples with Arbitrary Style Transfercited by 13
  5. 2023Reliable Evaluation of Adversarial Transferabilitycited by 12
  6. 2023Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical Worldcited by 11
  7. 2024Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Modelscited by 11
  8. 2023Improving Adversarial Transferability via Model Alignmentcited by 10
  9. 2023Boosting Adversarial Transferability with Learnable Patch-wise Maskscited by 8
  10. 2023Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Modelscited by 8
  11. 2022Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentationcited by 7
  12. 2023Adversarial Attack with Raindropscited by 7
  13. 2023Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Featurecited by 6
  14. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  15. 2024Improving Transferable Targeted Attacks with Feature Tuning Mixupcited by 6
  16. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  17. 2025Exploring Adversarial Transferability between Kolmogorov-arnold Networkscited by 4
  18. 2024Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferabilitycited by 3
  19. 2024Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixingcited by 3
  20. 2024Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustnesscited by 3
  21. 2024RenderBender: A Survey on Adversarial Attacks Using Differentiable Renderingcited by 3
  22. 2024Perturbation Towards Easy Samples Improves Targeted Adversarial Transferabilitycited by 2
  23. 2024S4ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attackcited by 1
  24. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  25. 2023A Survey of Adversarial CAPTCHAs on its History, Classification and Generationcited by 0
  26. 2023AutoAugment Input Transformation for Highly Transferable Targeted Attackscited by 0
  27. 2024Enhancing Adversarial Transferability via Information Bottleneck Constraintscited by 0
  28. 2024Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspectivecited by 0
  29. 2024Current Status and Trends in Image Anti-Forensics Research: A Bibliometric Analysiscited by 0
  30. 2024On the Robustness of Distributed Machine Learning against Transfer Attackscited by 0
  31. 2025Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approachcited by 0
  32. 2025RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruningcited by 0
  33. 2025Improving Black-Box Generative Attacks via Generator Semantic Consistencycited by 0
  34. 2025Semantically Guided Adversarial Testing of Vision Models Using Language Modelscited by 0
  35. 2025IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networkscited by 0
  36. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0
  37. 2026Beyond the Patch: Exploring Vulnerabilities of Visuomotor Policies via Viewpoint-Consistent 3D Adversarial Objectcited by 0