To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation

Wanlin Zhang, Weichen Lin, Ru Huang, Shihong Song, Hu Ding
2/12/2026

No official code found. Best implementation: USTC-DIAG-LAB/FDT (0 stars, last commit 2026-02-24).

Semantic Scholar

Code Implementations(1)

USTC-DIAG-LAB/FDTCommunity25%

Official implementation of "To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation" (ICLR 2025)

00Shell, PythonJul 14, 20257 months ago

Similar Papers

Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees

100% match1 repo102026

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

100% match1 repo82026

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

100% match1 repo152026

HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token Mining

100% match2026

Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms

99% match2026

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

99% match2026

Cite this paper

@article{zhang2026tackle,
  title  = {To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation},
  author = {Wanlin Zhang and Weichen Lin and Ru Huang and Shihong Song and Hu Ding},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:681b6a71d7d8afa01e07c5f76d19122b0863f254},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/681b6a71d7d8afa01e07c5f76d19122b0863f254.svg)](https://codeofpaper.com/paper/681b6a71d7d8afa01e07c5f76d19122b0863f254)

Discussion