Metraipolis › archive › dc_488ec32cff55

ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning — arXiv:2610.07323

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.07323
License (as archived): CC0-1.0
Archived: 2026-10-07T11:35:25.079Z
SHA-256 of the archived text: f24cba5f67410452617a8ea821701d2c0aad0b6b35f0ffd0cbe3d5dc77e27ce5
Stable URL of this page: https://metraipolis.com/documento/dc_488ec32cff55

How to cite

ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning — arXiv:2610.07323 — arXiv (en), https://arxiv.org/abs/2610.07323 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_488ec32cff55 (Metraipolis archive dc_488ec32cff55, sha256 f24cba5f67410452617a8ea821701d2c0aad0b6b35f0ffd0cbe3d5dc77e27ce5)

BibTeX

@misc{dc488ec32cff55,
  title = {ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning — arXiv:2610.07323},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07323},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_488ec32cff55; sha256 f24cba5f67410452617a8ea821701d2c0aad0b6b35f0ffd0cbe3d5dc77e27ce5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07323. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover \textit{sets} of inputs that induce model failure. We introduce ATLAS (Adaptive Trust-Regions for Latent Adversarial Searches), which is a query-based framework that discovers adversarial input sets for black-box learning systems. ATLAS casts attack generation as an active learning level set estimation problem then combines calibrated approximations with a local-global sampling architecture to find regions of the input space that contain adversarial examples. Once discovered, ATLAS is designed to sample points within these adversarial regions to build adversarial sets that accurately represent the state of robustness of the target model. When applied on toy experiments, we find that ATLAS is able to recover more of the adversarial region under a limited query budget than does previous work. When applied to standard and adversarially trained MNIST, CIFAR, and ImageNet model targets, ATLAS produces better representative attacks than other query-based black-box attacks (NES, SignHunter, BayesOpt). ATLAS represents an automated red-teaming framework that can be used for both analyzing the robustness of learning-based systems under development and continuous auditing to see how the robustness of a system changes over time.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
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/2610.07323 — 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 2026-10-07T11:18:39.718Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).