Metraipolis › archive › dc_bc3c3405b4e8

GuidedRay: Diversity-Guided Direction Discovery for Targeted Hard-Label Black-Box Attacks — arXiv:2609.25734

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25734
License (as archived)
CC0-1.0
Archived
2026-10-08T14:41:59.207Z
SHA-256 of the archived text
9bfe53f43f7aa3cdc956d39dee4b596194c2dfdb01f94f6c6ab7d9e889efedc8
Stable URL of this page
https://metraipolis.com/documento/dc_bc3c3405b4e8

How to cite

GuidedRay: Diversity-Guided Direction Discovery for Targeted Hard-Label Black-Box Attacks — arXiv:2609.25734 — arXiv (en), https://arxiv.org/abs/2609.25734 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc3c3405b4e8 (Metraipolis archive dc_bc3c3405b4e8, sha256 9bfe53f43f7aa3cdc956d39dee4b596194c2dfdb01f94f6c6ab7d9e889efedc8)
BibTeX
@misc{dcbc3c3405b4e8,
  title = {GuidedRay: Diversity-Guided Direction Discovery for Targeted Hard-Label Black-Box Attacks — arXiv:2609.25734},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25734},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc3c3405b4e8; sha256 9bfe53f43f7aa3cdc956d39dee4b596194c2dfdb01f94f6c6ab7d9e889efedc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25734. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep neural networks are vulnerable to adversarial attacks. Among black-box attacks, targeted decision-based attacks are particularly difficult: the attacker observes only the target model's top-1 label and aims to make it predict a prespecified target class under a bounded perturbation. Before perturbation refinement, the attacker must discover a direction that reaches the prescribed target region. This initialization step can incur substantial query cost. We propose GuidedRay, a targeted decision-based attack based on diversity-guided direction discovery. GuidedRay builds on two observations: target-class reference samples provide useful target-conditioned direction priors, and diverse candidates increase the probability of discovering a targeted adversarial direction. GuidedRay generates varied candidates from one or multiple target-class references and uses a one-query Fast Test to screen their induced sign directions. Once a feasible direction is found, GuidedRay applies Ray Search to reduce its decision-boundary radius. Experiments on CIFAR-10, CIFAR-100, and ImageNet demonstrate that GuidedRay consistently outperforms five state-of-the-art decision-based attacks at four evaluated query budgets from 500 to 5,000, with particularly pronounced gains in direction discovery during initialization. Against models protected by adversarial training or TRADES, it likewise achieves the highest attack success rate at all four query budgets.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.25734 — 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 2026-10-08T13:55:11.730Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).