mlsanityData to 13 Oct 2026

Superpixel Attack: Enhancing Black-box Adversarial Attack with Image-driven Division Areas

arXiv 2512.02062 ↗First posted 29 Nov 2025cs.CR cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small perturbations that can lead to misclassifications. More powerful black-box adversarial attacks are required to develop more effective defenses. A promising approach to black-box adversarial attacks is to repeat the process of extracting a specific image area and changing the perturbations added to it. Existing attacks adopt simple rectangles as the areas where perturbations are changed in a single iteration. We propose applying superpixels instead, which achieve a good balance between color variance and compactness. We also propose a new search method, versatile search, and a novel attack method, Superpixel Attack, which applies superpixels and performs versatile search. Superpixel Attack improves attack success rates by an average of 2.10% compared with existing attacks. Most models used in this study are robust against adversarial attacks, and this improvement is significant for black-box adversarial attacks. The code is avilable at https://github.com/oe1307/SuperpixelAttack.git.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 29 Nov 2025.

Builds on

20 of 31 references.

References · 20

  1. 2013Intriguing properties of neural networkscited by 5,137
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,992
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,445
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 902
  5. 2020Fast is better than free: Revisiting adversarial trainingcited by 725
  6. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 684
  7. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 658
  8. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  9. 2017On Detecting Adversarial Perturbationscited by 232
  10. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  11. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  12. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
8 more
  1. 2020GeoDA: a geometric framework for black-box adversarial attackscited by 66
  2. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  3. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  4. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  5. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  6. 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
  7. 2017Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regionscited by 21
  8. 2022Saliency Attack: Towards Imperceptible Black-box Adversarial Attackcited by 12

Built on by

Not cited yet.