STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks

Ankit Gupta, Akshat Pandya, Paul Lin, Christoph Adami, Emily Dolson

YAYIN:23 Eki 2026 ALAN:cs.CV

Özet

We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these perturbations through a lightweight greedy add-and-refine procedure. Across diverse image classifiers, STROKE achieves high attack success with low query counts at nominal 1--2% area settings, showing favorable performance relative to existing patch-based attacks in several configurations. Matched comparisons further demonstrate substantial reductions in wall-clock attack time, while ablation studies examine the key design choices and effectiveness across structural primitives. These findings suggest that simple structural occlusions offer an effective and computationally efficient search space for black-box adversarial attacks.

Özetle: We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions.

Özet

We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these perturbations through a lightweight greedy add-and-refine procedure. Across diverse image classifiers, STROKE achieves high attack success with low query counts at nominal 1–2% area settings, showing favorable performance relative to existing patch-based attacks in several configurations. Matched comparisons further demonstrate substantial reductions in wall-clock attack time, while ablation studies examine the key design choices and effectiveness across structural primitives. These findings suggest that simple structural occlusions offer an effective and computationally efficient search space for black-box adversarial attacks.

Orijinal Özet (İngilizce)

We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these perturbations through a lightweight greedy add-and-refine procedure. Across diverse image classifiers, STROKE achieves high attack success with low query counts at nominal 1–2% area settings, showing favorable performance relative to existing patch-based attacks in several configurations. Matched comparisons further demonstrate substantial reductions in wall-clock attack time, while ablation studies examine the key design choices and effectiveness across structural primitives. These findings suggest that simple structural occlusions offer an effective and computationally efficient search space for black-box adversarial attacks.

Kaynak: arXiv:2610.32932 · PDF

BibTeX

@article{gupta2026stroke,
  title   = {STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks},
  author  = {Ankit Gupta and Akshat Pandya and Paul Lin and Christoph Adami and Emily Dolson},
  journal = {arXiv preprint arXiv:2610.32932},
  year    = {2026},
  url     = {https://arxiv.org/abs/2610.32932}
}

Tartışma

Bu habere emoji ile tepki ver

İptal

Hizli:

Henüz yorum yok. İlk yorumu siz yapın!

Yapıcı ve saygılı yorumlar bekliyoruz. Topluluk kuralları