Boosting Adversarial Transferability via Ensemble Non-Attention Article Swipe

MAKE IMPACT

Yuan Zou , Qin Liu , Jie Wu , Guanrong Chen · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.08937

Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsatisfactory attack performance when transferring across heterogeneous model architectures. The main reason is that the gradient update directions of heterogeneous surrogate models differ widely, making it hard to reduce the gradient variance of ensemble models while making the best of individual model. To tackle this challenge, we design a novel ensemble attack, NAMEA, which for the first time integrates the gradients from the non-attention areas of ensemble models into the iterative gradient optimization process. Our design is inspired by the observation that the attention areas of heterogeneous models vary sharply, thus the non-attention areas of ViTs are likely to be the focus of CNNs and vice versa. Therefore, we merge the gradients respectively from the attention and non-attention areas of ensemble models so as to fuse the transfer information of CNNs and ViTs. Specifically, we pioneer a new way of decoupling the gradients of non-attention areas from those of attention areas, while merging gradients by meta-learning. Empirical evaluations on ImageNet dataset indicate that NAMEA outperforms AdaEA and SMER, the state-of-the-art ensemble attacks by an average of 15.0% and 9.6%, respectively. This work is the first attempt to explore the power of ensemble non-attention in boosting cross-architecture transferability, providing new insights into launching ensemble attacks.

Type

preprint

Landing Page

http://arxiv.org/abs/2511.08937

PDF

https://arxiv.org/pdf/2511.08937

OA Status

green

OpenAlex ID

https://openalex.org/W4416237359

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416237359

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2511.08937

Digital Object Identifier

Title

Boosting Adversarial Transferability via Ensemble Non-Attention

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-12

Full publication date if available

Authors

Yuan Zou, Qin Liu, Jie Wu, Guanrong Chen

List of authors in order

Landing page

https://arxiv.org/abs/2511.08937

Publisher landing page

PDF URL

https://arxiv.org/pdf/2511.08937

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2511.08937

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload