Transferable Attack for Semantic Segmentation
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and FGSM, do not transfer well to target models, making it necessary to study the transferable attacks, especially transferable attacks for semantic segmentation. We find two main factors to achieve transferable attack. Firstly, the attack should come with effective data augmentation and translation-invariant features to deal with unseen models. Secondly, stabilized optimization strategies are needed to find the optimal attack direction. Based on the above observations, we propose an ensemble attack for semantic segmentation to achieve more effective attacks with higher transferability. The source code and experimental results are publicly available via our project page: https://github.com/anucvers/TASS.
Code (1)
Tasks
Data AugmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
Transferable adversarial examples highlight the vulnerability of deep neural networks (DNNs) to imperceptible perturbations across various real-world applications. While there have been notable advancements in untargeted…
SegTrans: Transferable Adversarial Examples for Segmentation Models
Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across different segmentation models. While som…
Computational EfficiencyAdversarial AttackRethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective
Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink a…
Point CloudsTranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferability of adversarial examples on semantic s…
Adversarial Attackimage-classificationImage ClassificationSegmentation+1TransMedSeg: A Transferable Semantic Framework for Semi-Supervised Medical Image Segmentation
Semi-supervised learning (SSL) has achieved significant progress in medical image segmentation (SSMIS) through effective utilization of limited labeled data. While current SSL methods for medical images predominantly rel…
Image SegmentationMedical Image AnalysisMedical Image SegmentationRepresentation Learning+2