mlsanityData to 7 Oct 2026

Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent Space

arXiv 2305.12906 ↗First posted 22 May 2023cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks against Deep Neural Networks(DNN) have been a crutial topic ever since citegoodfellow purposed the vulnerability of DNNs. However, most prior works craft adversarial examples in the pixel space, following the lp norm constraint. In this paper, we give intuitional explain about why crafting adversarial examples in the latent space is equally efficient and important. We purpose a framework for crafting adversarial examples in semantic latent space based on an pre-trained Variational Auto Encoder from state-of-art Stable Diffusion ModelciteSDM. We also show that adversarial examples crafted in the latent space can also achieve a high level of fool rate. However, examples crafted from latent space are often hard to evaluated, as they doesn't follow a certain lp norm constraint, which is a big challenge for existing researches. To efficiently and accurately evaluate the adversarial examples crafted in the latent space, we purpose a novel evaluation matric based on SSIMciteSSIM loss and fool rate.Additionally, we explain why FIDciteFID is not suitable for measuring such adversarial examples. To the best of our knowledge, it's the first evaluation metrics that is specifically designed to evaluate the quality of a adversarial attack. We also investigate the transferability of adversarial examples crafted in the latent space and show that they have superiority over adversarial examples crafted in the pixel space.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

22 of 29 references.

References · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2016Adversarial Machine Learning at Scalecited by 934
  12. 2017Generating Natural Adversarial Examplescited by 182
10 more
  1. 2017Generative Adversarial Perturbationscited by 153
  2. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
  3. 2019Cross-Domain Transferability of Adversarial Perturbationscited by 92
  4. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  5. 2019AdvGAN++ : Harnessing latent layers for adversary generationcited by 20
  6. 2019AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examplescited by 17
  7. 2017LatentPoison - Adversarial Attacks On The Latent Spacecited by 9
  8. 2023Generating Adversarial Attacks in the Latent Spacecited by 8
  9. 2020AVAE: Adversarial Variational Auto Encodercited by 6
  10. 2020Generating Out of Distribution Adversarial Attack using Latent Space Poisoningcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2023Semantic Adversarial Attacks via Diffusion Models
  2. 2025SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
  3. 2026Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces
  4. 2023Complexity Matters: Rethinking the Latent Space for Generative Modeling
  5. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
  6. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
  7. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
  8. 2025ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models