Newest papers

Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online Feedback

Zhicheng Fang, Han Sun, Jiachen Lei, Xinyi Fang, Zongmin Zhang, Chenxu Fu, Sizhe Fang, Wei Xu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.25897 · open-access PDF

Korean

대형 언어 모델 (LLM)에 대한 자이블 브레이크 공격이 점점 다양해지면서, 레드팀은 자이블 브레이크 권고 및 공격 전략의 대규모 라이브러리에 의존하여 피해자 모델 및 방어 설정을 강력하게 평가합니다.그러나, 공격 효율성은 매우 조건에 의존합니다 : 한 피해자 방어 설정에서 성공하는 공격은 다른 하나에서 실패할 수 있으며, 각 설정에 대한 전체 공격 라이브러리를 철저하게 평가하면 상당한 토큰 및 화폐 비용이 발생합니다.

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

Abstract

As jailbreak attacks against large language models (LLMs) become increasingly diverse, red-teaming has come to rely on large libraries of jailbreak prompts and attack strategies to evaluate the robustness of victim models and their defense settings. However, attack effectiveness is highly condition-dependent: an attack that succeeds under one victim-defense setting may fail under another, while exhaustively evaluating the full attack library for each setting incurs substantial token and monetary costs. This motivates studying how jailbreak attacks should be prioritized under a limited attempt

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

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