mlsanityData to 14 Oct 2026

A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement

arXiv 2506.23676 ↗First posted 30 Jun 2025cs.CVcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion model, these diffusion-based methods often struggle to generalize beyond conventional image classification tasks, such as in Deepfake detection. Moreover, traditional strategies for enhancing adversarial example transferability are challenging to adapt to these methods. To address these challenges, we propose a unified framework that seamlessly incorporates traditional transferability enhancement strategies into diffusion model-based adversarial example generation via image editing, enabling their application across a wider range of downstream tasks. Our method won first place in the "1st Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Media" competition at ACM MM25, which validates the effectiveness of our approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 28 of its 39 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

28 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attack14 May

Other references · 27

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  11. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 647
  12. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
15 more
  1. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  2. 2019Object Detection in 20 Years: A Surveycited by 531
  3. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  4. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  5. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 319
  6. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  7. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  8. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  9. 2020SurFree: a fast surrogate-free black-box attackcited by 60
  10. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 37
  11. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  12. 2025When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learningcited by 14
  13. 2024StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Modelcited by 12
  14. 2024Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrievalcited by 9
  15. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attackscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models
  2. 2023Mist: Towards Improved Adversarial Examples for Diffusion Models
  3. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
  4. 2023Improving Adversarial Transferability by Stable Diffusion
  5. 2025Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
  6. 2024Deceptive Diffusion: Generating Synthetic Adversarial Examples
  7. 2025ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
  8. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds