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
Karena serangan jailbreak terhadap model bahasa besar (LLM) menjadi semakin beragam, red-teaming telah bergantung pada perpustakaan besar petunjuk jailbreak dan strategi serangan untuk mengevaluasi ketahanan model korban dan pengaturan pertahanan mereka. Namun, efektivitas serangan sangat tergantung pada kondisi: serangan yang berhasil di bawah satu pengaturan pertahanan korban mungkin gagal di bawah yang lain, sementara mengevaluasi secara menyeluruh perpustakaan serangan penuh untuk setiap pengaturan menimbulkan biaya token dan moneter yang substansial.
Machine translation (Meta M2M100); the English original follows.
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
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25897, 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