Lune

AAAI2024Top-tier venue

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

Qinliang Lin, Cheng Luo, Zenghao Niu, Xilin He, Weicheng Xie, Yuanbo Hou, Linlin Shen, Siyang Song

Abstract

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, De-CoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (De-CoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://github.com/LinQinLiang/DeCoWA .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

6 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Boosting Adversarial Transferability through Augmentation in Hypothesis Space cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Boosting Adversarial Transferability through Augmentation in Hypothesis Space cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers cites Training data-efficient image transformers & distillation through attention
  • Is Space-Time Attention All You Need for Video Understanding? cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Training data-efficient image transformers & distillation through attention
  • Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • Training data-efficient image transformers & distillation through attention cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers6

  1. Transferable Adversarial Attacks on SAM and Its Downstream ModelsSong Xia, Wenhan Yang, Yi Yu, Xun Lin et al.NeurIPS 2024 · 29 citations
  2. ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision TransformersHanwen Cao, Haobo Lu, Xiaosen Wang, Kun HeICCV 2025 · 5 citations
  3. OTI: A Model-free and Visually Interpretable Measure of Image AttackabilityJiaming Liang, Haowei Liu, Chi-Man PunAAAI 2026 · 1 citation
  4. Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty ReductionJin Hu, Jiakai Wang, Linna Jing, Haolin Li et al.NeurIPS 2025 · 1 citation
  5. Boosting Adversarial Transferability through Augmentation in Hypothesis SpaceYu Guo, Weiquan Liu, Qingshan Xu, Shijun Zheng et al.CVPR 2025

Builds on27

  1. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  2. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  3. Training data-efficient image transformers & distillation through attentionHugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa et al.ICML 2021 · 8,974 citations
  4. FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceKihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang et al.NeurIPS 2020 · 5,129 citations
  5. Is Space-Time Attention All You Need for Video Understanding?Gedas Bertasius, Heng Wang, Lorenzo TorresaniICML 2021 · 2,927 citations

Related papers

  1. Learning to Learn Transferable AttackShuman Fang, Jie Li, Xianming Lin, Rongrong JiAAAI 2022 · 26 citations
  2. Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box DomainsQilong Zhang, Xiaodan Li, Yuefeng Chen, Jingkuan Song et al.ICLR 2022 · 85 citations
  3. CDTA: A Cross-Domain Transfer-Based Attack with Contrastive LearningZihan Li, Weibin Wu, Yuxin Su, Zibin Zheng et al.AAAI 2023 · 14 citations
  4. Boosting the Transferability of Adversarial Attacks with Reverse Adversarial PerturbationZeyu Qin, Yanbo Fan, Yi Liu, Li Shen et al.NeurIPS 2022 · 135 citations
  5. CT-GAT: Cross-Task Generative Adversarial Attack based on TransferabilityMinxuan Lv, Chengwei Dai, Kun Li, Wei Zhou et al.EMNLP 2023 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines