Related papers: IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks

IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks

URL: http://arxiv.org/abs/2607.27465v1
Date: Wed, 29 Jul 2026 21:08:48 GMT
Title: IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks
Abstract summary: This paper studies an efficient single-source alternative for transferable attacks on semantic segmentation.<n>We formulate transferable attack composition as a chained computation over differentiable attack components.<n>Experiments on Pascal VOC and Cityscapes evaluate the resulting transferability efficiency trade-off across CNN- and transformer-based segmentation models.
Score: 8.87804866046385
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be computationally expensive. Existing ensemble attacks often rely on multiple surrogate models, increasing the computation cost, even harder for segmentation. This paper studies an efficient single-source alternative for transferable attacks on semantic segmentation. We formulate transferable attack composition as a chained computation over differentiable attack components, allowing the expensive source-model gradient computation to be shared. To reduce the update instability introduced by chained composition, we further use an integrated-gradient-style path-averaged direction as an empirical stabilization heuristic. Experiments on Pascal VOC and Cityscapes evaluate the resulting transferability efficiency trade-off across CNN- and transformer-based segmentation models. IGME achieves competitive transferability compared with single-source baselines and favorable runtime compared with model-ensemble attacks, while requiring access to only one source model.

Related papers

Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
arXiv Detail & Related papers (2026-07-08T09:27:15Z)
SegTrans: Transferable Adversarial Examples for Segmentation Models [47.89859018981832]
Existing adversarial attack methods show poor transferability across different segmentation models.<n>We propose SegTrans, a novel transfer attack framework that divides the input sample into multiple local regions.<n>SegTrans only retains local semantic information from the original input, rather than using global semantic information to optimize perturbations.
arXiv Detail & Related papers (2025-10-10T02:11:29Z)
A Simple DropConnect Approach to Transfer-based Targeted Attack [43.039945949426546]
We study the problem of transfer-based black-box attack, where adversarial samples generated using a single surrogate model are directly applied to target models.<n>We propose to Mitigate perturbation Co-adaptation by DropConnect to enhance transferability.<n>In the challenging scenario of transferring from a CNN-based model to Transformer-based models, MCD achieves 13% higher average ASRs compared with state-of-the-art baselines.
arXiv Detail & Related papers (2025-04-24T12:29:23Z)
Enhancing Adversarial Transferability with Adversarial Weight Tuning [50.01825144613307]
adversarial examples (AEs) mislead the model while appearing benign to human observers.<n>AWT is a data-free tuning method that combines gradient-based and model-based attack methods to enhance the transferability of AEs.
arXiv Detail & Related papers (2024-08-18T13:31:26Z)
Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation [49.480978190805125]
Transfer attacks generate significant interest for black-box applications. Existing works essentially directly optimize the single-level objective w.r.t. surrogate model. We propose a bilevel optimization paradigm, which explicitly reforms the nested relationship between the Upper-Level (UL) pseudo-victim attacker and the Lower-Level (LL) surrogate attacker.
arXiv Detail & Related papers (2024-06-04T07:45:27Z)
Transferable Attack for Semantic Segmentation [59.17710830038692]
adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. We propose an ensemble attack for semantic segmentation to achieve more effective attacks with higher transferability.
arXiv Detail & Related papers (2023-07-31T11:05:55Z)
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability [20.255708227671573]
Black-box adversarial attacks can be transferred from one model to another. In this work, we propose a novel ensemble attack method called the variance reduced ensemble attack. Empirical results on the standard ImageNet demonstrate that the proposed method could boost the adversarial transferability and outperforms existing ensemble attacks significantly.
arXiv Detail & Related papers (2021-11-21T06:33:27Z)
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution [83.02632136860976]
We study black-box adversarial attacks against deep neural networks (DNNs) We develop a novel mechanism of adversarial transferability, which is robust to the surrogate biases. Experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method.
arXiv Detail & Related papers (2020-06-15T16:45:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.