# Towards Transferable Adversarial Attacks on Vision Transformers

arXiv: https://arxiv.org/abs/2109.04176 · HTML: https://mlsanity.com/paper/2109.04176/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Rethinking Spatial Dimensions of Vision Transformers](https://mlsanity.com/paper/2103.16302/) (2021)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [DeepViT: Towards Deeper Vision Transformer](https://mlsanity.com/paper/2103.11886/) (2021)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets](https://mlsanity.com/paper/2002.05990/) (2020)
- [Visformer: The Vision-friendly Transformer](https://mlsanity.com/paper/2104.12533/) (2021)
- [Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World](https://mlsanity.com/paper/2103.01050/) (2021)
- [M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection](https://mlsanity.com/paper/2104.09770/) (2021)
- [A Unified Approach to Interpreting and Boosting Adversarial Transferability](https://mlsanity.com/paper/2010.04055/) (2020)
- [On Improving Adversarial Transferability of Vision Transformers](https://mlsanity.com/paper/2106.04169/) (2021)

## Built on by (most cited first, 30 of 80)

- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Jailbreaking Attack against Multimodal Large Language Model](https://mlsanity.com/paper/2402.02309/) (2024)
- [Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models](https://mlsanity.com/paper/2307.14061/) (2023)
- [VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models](https://mlsanity.com/paper/2310.04655/) (2023)
- [Physical Adversarial Attack meets Computer Vision: A Decade Survey](https://mlsanity.com/paper/2209.15179/) (2022)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs](https://mlsanity.com/paper/2110.02797/) (2021)
- [Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?](https://mlsanity.com/paper/2203.08392/) (2022)
- [Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization](https://mlsanity.com/paper/2303.15754/) (2023)
- [SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation](https://mlsanity.com/paper/2312.04913/) (2023)
- [Enhancing the Self-Universality for Transferable Targeted Attacks](https://mlsanity.com/paper/2209.03716/) (2022)
- [Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness](https://mlsanity.com/paper/2203.13639/) (2022)
- [Exploring the Relationship between Architecture and Adversarially Robust Generalization](https://mlsanity.com/paper/2209.14105/) (2022)
- [Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2204.07932/) (2022)
- [Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping](https://mlsanity.com/paper/2402.03951/) (2024)
- [Improved Generation of Adversarial Examples Against Safety-aligned LLMs](https://mlsanity.com/paper/2405.20778/) (2024)
- [Attacking Video Recognition Models with Bullet-Screen Comments](https://mlsanity.com/paper/2110.15629/) (2021)
- [Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal](https://mlsanity.com/paper/2112.03492/) (2021)
- [Reliable Evaluation of Adversarial Transferability](https://mlsanity.com/paper/2306.08565/) (2023)
- [Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting](https://mlsanity.com/paper/2308.10315/) (2023)
- [Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks](https://mlsanity.com/paper/2309.13609/) (2023)
- [On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective](https://mlsanity.com/paper/2408.13809/) (2024)
- [Improving Adversarial Transferability via Model Alignment](https://mlsanity.com/paper/2311.18495/) (2023)
- [Adventures of Trustworthy Vision-Language Models: A Survey](https://mlsanity.com/paper/2312.04231/) (2023)
- [Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics](https://mlsanity.com/paper/2501.08415/) (2025)
- [Boosting Adversarial Transferability with Learnable Patch-wise Masks](https://mlsanity.com/paper/2306.15931/) (2023)
- [VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models](https://mlsanity.com/paper/2505.17440/) (2025)
- [Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement](https://mlsanity.com/paper/2503.15404/) (2025)
- [Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly](https://mlsanity.com/paper/2311.01323/) (2023)
- [Long-term Leap Attention, Short-term Periodic Shift for Video Classification](https://mlsanity.com/paper/2207.05526/) (2022)

## Abstract (arXiv)

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fashion as CNNs. In this paper, we posit that adversarial attacks on transformers should be specially tailored for their architecture, jointly considering both patches and self-attention, in order to achieve high transferability. More specifically, we introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs. We show that skipping the gradients of attention during backpropagation can generate adversarial examples with high transferability. In addition, adversarial perturbations generated by optimizing randomly sampled subsets of patches at each iteration achieve higher attack success rates than attacks using all patches. We evaluate the transferability of attacks on state-of-the-art ViTs, CNNs and robustly trained CNNs. The results of these experiments demonstrate that the proposed dual attack can greatly boost transferability between ViTs and from ViTs to CNNs. In addition, the proposed method can easily be combined with existing transfer methods to boost performance. Code is available at https://github.com/zhipeng-wei/PNA-PatchOut.