mlsanityData to 7 Oct 2026

Semantic Adversarial Examples

arXiv 1804.00499 ↗First posted 16 Mar 2018cs.CV cs.AI cs.LGcited by 86

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the model prediction error. Such images, however, contain artificial perturbations that make them somewhat distinguishable from natural images. This property is used by several defense methods to counter adversarial examples by applying denoising filters or training the model to be robust to small perturbations. In this paper, we introduce a new class of adversarial examples, namely "Semantic Adversarial Examples," as images that are arbitrarily perturbed to fool the model, but in such a way that the modified image semantically represents the same object as the original image. We formulate the problem of generating such images as a constrained optimization problem and develop an adversarial transformation based on the shape bias property of human cognitive system. In our method, we generate adversarial images by first converting the RGB image into the HSV (Hue, Saturation and Value) color space and then randomly shifting the Hue and Saturation components, while keeping the Value component the same. Our experimental results on CIFAR10 dataset show that the accuracy of VGG16 network on adversarial color-shifted images is 5.7%.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 27; 2023: 20; 2024: 8; 2025: 11; 2026: 4.

86 papers.

Sort:

By area:

  1. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  4. 2023Content-based Unrestricted Adversarial Attackcited by 73
  5. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  6. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  7. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  8. 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbationscited by 26
  9. 2022GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothingcited by 23
  10. 2021Robustness and Generalization via Generative Adversarial Trainingcited by 20
  11. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  12. 2021Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similaritycited by 18
38 more
  1. 2021CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networkscited by 18
  2. 2022Attacking deep networks with surrogate-based adversarial black-box methods is easycited by 18
  3. 2022StyleFool: Fooling Video Classification Systems via Style Transfercited by 18
  4. 2022Unrestricted Black-box Adversarial Attack Using GAN with Limited Queriescited by 18
  5. 2023Instruct2Attack: Language-Guided Semantic Adversarial Attackscited by 16
  6. 2023AdvST: Revisiting Data Augmentations for Single Domain Generalizationcited by 16
  7. 2022Towards Transferable Unrestricted Adversarial Examples with Minimum Changescited by 13
  8. 2023Semantic Adversarial Attacks via Diffusion Modelscited by 12
  9. 2021Exposing Previously Undetectable Faults in Deep Neural Networkscited by 11
  10. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  11. 2022Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNscited by 11
  12. 2022Adversarial Color Film: Effective Physical-World Attack to DNNscited by 11
  13. 2022On the Origins of the Block Structure Phenomenon in Neural Network Representationscited by 10
  14. 2022Adversarially Robust Learning with Tolerancecited by 9
  15. 2022Hierarchical Distribution-Aware Testing of Deep Learningcited by 8
  16. 2023Attacking Perceptual Similarity Metricscited by 8
  17. 2021Imperceptible Adversarial Examples by Spatial Chroma-Shiftcited by 7
  18. 2022NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learningcited by 7
  19. 2025"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Modelscited by 7
  20. 2021Simple Transparent Adversarial Examplescited by 6
  21. 2022Adversarial Neon Beam: A Light-based Physical Attack to DNNscited by 6
  22. 2022Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectorscited by 6
  23. 2023Optimization and Optimizers for Adversarial Robustnesscited by 6
  24. 2025Beyond Statistical Learning: Exact Learning Is Essential for General Intelligencecited by 6
  25. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  26. 2022CARBEN: Composite Adversarial Robustness Benchmarkcited by 5
  27. 2021Effective Universal Unrestricted Adversarial Attacks using a MOE Approachcited by 4
  28. 2021Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilitiescited by 4
  29. 2021Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Networkcited by 4
  30. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4
  31. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4
  32. 2023CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Spacecited by 4
  33. 2023Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimizationcited by 4
  34. 2024Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semanticscited by 4
  35. 2024Natural Language Induced Adversarial Imagescited by 4
  36. 2021In-distribution adversarial attacks on object recognition models using gradient-free searchcited by 3
  37. 2022Optimization for Robustness Evaluation beyond ℓp Metricscited by 3
  38. 2022Addressing Mistake Severity in Neural Networks with Semantic Knowledgecited by 3

50 most cited of 86 All 86 (JSON)