Metraipolis › archive › dc_971ffc1c69fd

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision — arXiv:2609.24249

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24249
License (as archived)
CC0-1.0
Archived
2026-10-09T07:01:19.549Z
SHA-256 of the archived text
691be895a388ee4fabd0ad8826a7cc4d3bde488c0b2e47d43c30987a54ce170a
Stable URL of this page
https://metraipolis.com/documento/dc_971ffc1c69fd

How to cite

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision — arXiv:2609.24249 — arXiv (en), https://arxiv.org/abs/2609.24249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_971ffc1c69fd (Metraipolis archive dc_971ffc1c69fd, sha256 691be895a388ee4fabd0ad8826a7cc4d3bde488c0b2e47d43c30987a54ce170a)
BibTeX
@misc{dc971ffc1c69fd,
  title = {Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision — arXiv:2609.24249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_971ffc1c69fd; sha256 691be895a388ee4fabd0ad8826a7cc4d3bde488c0b2e47d43c30987a54ce170a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These adversarial attacks are often considered to be a significant threat to the implementation of neural networks in safety-critical applications. Most attacks utilize the white-box threat model and therefore require full access to the target model, making them unrealistic to use in practice. We propose a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model. Reinforcement learning algorithms have already been optimized to be query efficient, making them an ideal starting point when designing black-box adversarial attacks. We show the success of our reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model, by comparing it to state of the art attacks on different models on the Cifar10 and ImageNet data sets. RIBA takes $25.4\%$ fewer median queries to generate attacked images against a ResNet-18 on Cifar10 and $22.5\%$ fewer median queries to fool a Vit-B/16 model on ImageNet. Additionally, we demonstrate that RIBA can match the performance of white-box attacks on an adversarially trained model.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CR).
Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.24249 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:56:01.034Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).