Metraipolis › archive › dc_05af6bbf867b
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness — arXiv:2610.27353
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.27353
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:07:40.848Z
- SHA-256 of the archived text
8d1508d6185de27356eb3bd5c62c9c031b29dbf3e5b3cb2b52102c4fff7f5249- Stable URL of this page
https://metraipolis.com/documento/dc_05af6bbf867b
How to cite
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness — arXiv:2610.27353 — arXiv (en), https://arxiv.org/abs/2610.27353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05af6bbf867b (Metraipolis archive dc_05af6bbf867b, sha256 8d1508d6185de27356eb3bd5c62c9c031b29dbf3e5b3cb2b52102c4fff7f5249)
BibTeX
@misc{dc05af6bbf867b,
title = {Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness — arXiv:2610.27353},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.27353},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05af6bbf867b; sha256 8d1508d6185de27356eb3bd5c62c9c031b29dbf3e5b3cb2b52102c4fff7f5249},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillation methods, and data. These shared algorithmic choices can expose an otherwise distinct model ecosystem to concentrated risks leading to a vulnerability monoculture. Yet current practice in assessing adversarial robustness is restricted to individual robustness scores and attack transfer rates, leaving open the unexplored fundamental question: how many attacks suffice for catastrophic widespread compromise? In this paper, we investigate the empirical nature of shared vulnerabilities within a model pool and introduce Systemic Adversarial Robustness (SAR), a novel measure of shared vulnerability of a model pool through the attack diversity needed to exploit it. Specifically, SAR interpolates between single-attack transferability and independent per-model robustness: small values reveal a vulnerability monoculture, whereas large values indicate that failures are dispersed across models. We theoretically formulate SAR as a partial set-cover problem with provable approximation guarantees---enabling the development of scalable algorithms to empirically measure the systemic adversarial robustness. We empirically test the shared vulnerability of vision and large language models and characterize their shared collective vulnerability curve. Specifically, we demonstrate that model pools distilled from DeepSeek-R1 and Claude Opus 4.6 exhibit lower estimated systemic robustness than their corresponding parent pools, revealing a potential systemic cost of frontier-model distillation. Our framework seeks to establish vulnerability monoculture as a measurable target for a more wholistic adversarial evaluation of model populations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.27353 — 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 2026-10-21T07:05:43.551Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).