mlsanityData to 14 Oct 2026

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation

arXiv 2412.16651 ↗First posted 21 Dec 2024cs.CV cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

22 of 38 references.

References · 22

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  3. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  4. 2016Pyramid Scene Parsing Networkcited by 2,479
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  6. 2016Universal adversarial perturbationscited by 784
  7. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  8. 2023AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learningcited by 103
  9. 2018CGNet: A Light-weight Context Guided Network for Semantic Segmentationcited by 94
  10. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  11. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  12. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
10 more
  1. 2020Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspectivecited by 59
  2. 2024BadRobot: Jailbreaking Embodied LLM Agents in the Physical Worldcited by 43
  3. 2023Downstream-agnostic Adversarial Examplescited by 32
  4. 2024DarkSAM: Fooling Segment Anything Model to Segment Nothingcited by 32
  5. 2022BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Labelcited by 28
  6. 2024Transferable Adversarial Facial Images for Privacy Protectioncited by 27
  7. 2024Securely Fine-tuning Pre-trained Encoders Against Adversarial Examplescited by 21
  8. 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Needcited by 16
  9. 2023Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learningcited by 10
  10. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 8; 2026: 4.

14 papers.

Sort:

By area:

  1. 2025ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agentscited by 23
  2. 2025X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPcited by 21
  3. 2024NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectorscited by 17
  4. 2025Test-Time Backdoor Detection for Object Detection Modelscited by 14
  5. 2024Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Featurecited by 13
  6. 2025Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2cited by 11
  7. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  8. 2025SegTrans: Transferable Adversarial Examples for Segmentation Modelscited by 8
  9. 2025DarkHash: A Data-Free Backdoor Attack Against Deep Hashingcited by 6
  10. 2026Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustnesscited by 3
  11. 2026Transferable Physical-World Adversarial Patches Against Pedestrian Detection Modelscited by 2
  12. 2025Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Facescited by 1
2 more
  1. 2026Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Drivingcited by 1
  2. 2026VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasioncited by 0