PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model's predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial Attackimage-classificationImage ClassificationImage SegmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Universal Adversarial Perturbations Against Semantic Image Segmentation
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated speci…
image-classificationImage ClassificationImage SegmentationSegmentation+1OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wid…
Semantic SegmentationAutonomous DrivingSegment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models
General purpose segmentation models are able to generate (semantic) segmentation masks from a variety of prompts, including visual (points, boxed, etc.) and textual (object names) ones. In particular, input images are pr…
SegmentationSemantic SegmentationAdversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation
Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models (VLSMs) is still under-explored, especia…
Adversarial AttackAdversarial RobustnessImage SegmentationMedical Image Analysis+3Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series …
object-detectionObject DetectionSemantic Segmentation