Newest papers

Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness

Leo Elmecker-Plakolm, Łukasz Szpruch, Avishek Joey Bose, Matthew Wicker · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27353 · cited by 0 works (OpenAlex) · open-access PDF

Korean

이러한 공유 알고리즘 선택은 다른 방식으로 구분된 모델 생태계를 취약성 monoculture로 이어지는 집중된 위험에 노출시킬 수 있습니다.그러나 현재의 관행은 모형 폴 내에서 공유 비용 취약성의 실험적 성격을 조사하고 시스템 Adversarial Robustness (SAR)를 도입하고, 그것을 이용하는 데 필요한 더 낮은 공격 다양성을 통해 풀의 공유 취약성 모델의 새로운 측정입니다.특히, 우리의 SAR는 단일 공격 전송성과 독립적 인 패턴 robustness 사이의 인터폴라를 보여줍니다.이 논문에서, 우리는 작은 프론티컬 값을 보여줍니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Adversarial system, Robustness (evolution), Computer science, Exploit, Vulnerability (computing), Vulnerability assessment

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange