EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A Texture-Guided Adversarial Defense Framework Against Deepfake Generation

Maryam Bukhari, Muazzam Maqsood, Asma Sattar, Mi Young Lee

IEEE Access · 2026 · 14 · 45017-45037

DOI: 10.1109/access.2026.3673428 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Maryam Bukhari und 3 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea (NRF) grant, Korean Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deepfakes are an increasing danger to the reliability of digital media, with several detection algorithms developed to identify manipulated content. Although detection approaches continue to improve, proactive defenses that protect images by embedding imperceptible adversarial perturbations before distribution, thereby preventing deepfake generation at the source, offer a more robust complementary solution. However, existing proactive adversarial defenses against deepfake generators suffer from three key limitations: poor imperceptibility, limited texture-level targeting, and a lack of control over low-level structure perturbation. To address this, a novel patch-wise texture-aware adversarial attack is proposed as a proactive defense that disrupts deepfake generation. This is because adversarial images are generated through the addition of perturbations to the original facial images, so maintaining visual imperceptibility is a critical requirement; thus, our defense explicitly focuses on limiting perturbations to low-energy texture aspects that do not significantly affect human perception. The proposed method leverages tail-mode singular vectors extracted via patch-wise Singular Value Decomposition (SVD) to amplify low-energy texture components, i.e., producing adversarial perturbations that remain visually imperceptible while degrading the quality of generated deepfake images. Additionally, we introduce a variant that performs gradient projection into the SVD-tail subspace, ensuring that updates stay confined to subtle texture patterns and avoid high-frequency noise. The findings show that the proposed method is a stealthier attack that disrupts deepfake generations. Experimental results show that the proposed method achieves high attack success rates while preserving perceptual similarity, outperforming baselines in terms of imperceptibility and effectiveness. This work demonstrates a novel pathway toward proactive and imperceptible defenses against deepfake generation.

Förderung

  • National Research Foundation of Korea (NRF) grant
  • Korean Government

Zitieren

APA

Bukhari, M., Maqsood, M., Sattar, A., & Lee, M. Y. (2026). A Texture-Guided Adversarial Defense Framework Against Deepfake Generation. IEEE Access, 14, 45017-45037. https://doi.org/10.1109/access.2026.3673428

Vancouver

Bukhari M, Maqsood M, Sattar A, Lee MY. A Texture-Guided Adversarial Defense Framework Against Deepfake Generation. IEEE Access. 2026;14:45017-45037. doi:10.1109/access.2026.3673428

BibTeX
@article{Bukhari2026,
  author = {Bukhari, Maryam and Maqsood, Muazzam and Sattar, Asma and Lee, Mi Young},
  title = {A Texture-Guided Adversarial Defense Framework Against Deepfake Generation},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {45017--45037},
  doi = {10.1109/access.2026.3673428}
}
Kostenlos starten →