Skip to content
AI News HubLIVE
Original source2 min read

IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks

Summary

The paper proposes IGME, an efficient single-source chained method ensemble for transferable semantic segmentation attacks. It formulates attack composition as a chained computation over differentiable components to share source-model gradients, and uses an integrated-gradient-style path-averaged direction for stability. Experiments on Pascal VOC and Cityscapes show competitive transferability versus single-source baselines and favorable runtime versus model-ensemble attacks while requiring only one source model.

SourcearXiv Computer VisionAuthor: Mengqi He, Jing Zhang
IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 29 Jul 2026]

Title:IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks

View a PDF of the paper titled IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks, by Mengqi He and 1 other authors

View PDF HTML (experimental)

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.

Comments: 8 pages, 3 figures

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

ACM classes: I.2.10; I.4.6

Cite as: arXiv:2607.27465 [cs.CV]

(or arXiv:2607.27465v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2607.27465

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mengqi He [view email] [v1] Wed, 29 Jul 2026 21:08:48 UTC (6,449 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks, by Mengqi He and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Formulates transferable attack composition as a chained computation over differentiable attack components, sharing expensive source-model gradient computation
  • Uses an integrated-gradient-style path-averaged direction as an empirical stabilization heuristic to reduce update instability from chained composition
  • Evaluates the transferability-efficiency trade-off on Pascal VOC and Cityscapes across CNN- and transformer-based segmentation models
  • Achieves competitive transferability compared with single-source baselines and favorable runtime compared with model-ensemble attacks using only one source model

Highlights and analysis are generated automatically and may contain errors. Check the original source.