Leo Elmecker-Plakolm, Lukasz Szpruch, Avishek Joey Bose, Matthew Wicker · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27353 · open-access PDF
Di bawah keanekaragaman yang jelas dari model dasar terletak tumpukan teknis yang semakin homogen dari pipa pelatihan umum, metode distilasi, dan data. Pilihan algoritmik bersama ini dapat mengekspos ekosistem model yang berbeda untuk risiko terkonsentrasi yang mengarah ke monokultur kerentanan. Namun, praktek saat ini dalam menilai ketahanan lawan terbatas pada skor ketahanan individu dan tingkat transfer serangan, meninggalkan pertanyaan fundamental yang belum dijelaskan: berapa banyak serangan yang cukup untuk kompromi yang luas?
Machine translation (Meta M2M100); the English original follows.
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 natu
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27353, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange