EUVIMEDEUVIMED entdecken
Crossref

FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis

Shuo Liu, Xianghong Lin, Yukun Wei, Zhongliang Yang

IEEE Signal Processing Letters · 2026 · 33 · 2485-2489

DOI: 10.1109/lsp.2026.3700567 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Shuo Liu und 3 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. However, detection is severely hampered by two fundamental issues during model training. Firstly, extreme class imbalance (less than 1% steganographic samples) induces a strong decision bias. Secondly, the invisibility of generative steganography means its features are nearly indistinguishable from benign text; this similarity, compounded by their extreme rarity, leads to severe feature marginalization, where faint steganographic signals are completely overwhelmed. To directly address these optimization-level challenges, we propose FADRW (Feature-Aware Modulated and Dynamically Reweighted Loss), a novel loss function framework engineered for few-shot steganalysis. FADRW employs Dynamic Reweighting to progressively counteract decision bias, and a Feature-Aware Modulation module to structurally reshape the feature space, preventing feature marginalization by enhancing the separability of these subtle features. Extensive experiments on datasets from three real-world social platforms demonstrate that FADRW significantly outperforms state-of-the-art methods, particularly in the challenging few-shot steganographic sample scenario.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Liu, S., Lin, X., Wei, Y., & Yang, Z. (2026). FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis. IEEE Signal Processing Letters, 33, 2485-2489. https://doi.org/10.1109/lsp.2026.3700567

Vancouver

Liu S, Lin X, Wei Y, Yang Z. FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis. IEEE Signal Processing Letters. 2026;33:2485-2489. doi:10.1109/lsp.2026.3700567

BibTeX
@article{Liu2026,
  author = {Liu, Shuo and Lin, Xianghong and Wei, Yukun and Yang, Zhongliang},
  title = {FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2485--2489},
  doi = {10.1109/lsp.2026.3700567}
}
Kostenlos starten →