mlsanityData to 14 Oct 2026

Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector

arXiv 2511.15571 ↗First posted 19 Nov 2025cs.CV cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition. In view of antiforensics, it is significant to develop advanced adversarial attacks for evaluating the security of such detectors, which remains unexplored sufficiently. This letter proposes a Dual-domain Feature Importance Attack (DuFIA) scheme to invalidate AIGI detectors to some extent. Forensically important features are captured by the spatially interpolated gradient and frequency-aware perturbation. The adversarial transferability is enhanced by jointly modeling spatial and frequency-domain feature importances, which are fused to guide the optimization-based adversarial example generation. Extensive experiments across various AIGI detectors verify the cross-model transferability, transparency and robustness of DuFIA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 19 Nov 2025.

Builds on

25 of 33 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Adversarial examples in the physical worldcited by 1,769
  8. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  9. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  10. 2022On the detection of synthetic images generated by diffusion modelscited by 283
  11. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 280
  12. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
13 more
  1. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  2. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 130
  3. 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
  4. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  5. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  6. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  7. 2024Aligned Datasets Improve Detection of Latent Diffusion-Generated Imagescited by 36
  8. 2020FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstructioncited by 33
  9. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  10. 2018Task-generalizable Adversarial Attack based on Perceptual Metriccited by 18
  11. 2024Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attackscited by 12
  12. 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detectioncited by 11
  13. 2022Black-Box Attack against GAN-Generated Image Detector with Contrastive Perturbationcited by 2

Built on by

Not cited yet.