Journal of Information Security Reserach ›› 2026, Vol. 12 ›› Issue (E1): 216-220.
Previous Articles Next Articles
Online:2026-09-04
Published:2026-09-04
魏治锬,杜旭冉,张雪健
| [1] Huang X, Qin S, Jia X, et al. Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search [EB/OL]. 2026[2026-04-27]. http://arxiv.org/pdf/2602.22983. [2] Yuan Y, Jiao W, Wang W, et al. Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher [EB/OL]. 2026[2026-04-27]. http://arxiv.org/pdf/2308.06463. [3] Wang H, Li H, Huang M, et al. Asetf: A novel method for jailbreak attack on llms through translate suffix embeddings [EB/OL]. 2024[2026-04-27]. http://arxiv.org/pdf/2402.16006. [4] Ren Q, Li H, Liu D, et al. Llms know their vulnerabilities: Uncover safety gaps through natural distribution shifts [EB/OL]. 2024[2026-04-27]. http://arxiv.org/abs/2410.10700v2. [5] Russinovich M, Salem A, Eldan R. Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack [EB/OL]. 2024[2026-04-27]. http://arxiv.org/pdf/2404.01833. [6] Yang X, Tang X, Hu S, et al. Chain of attack: a semantic-driven contextual multi-turn attacker for llm [EB/OL]. 2024[2026-04-27]. http://arxiv.org/pdf/2405.05610. [7] Ying Z, Zhang D, Jing Z, et al. Reasoning-augmented conversation for multi-turn jailbreak attacks on large language models [EB/OL]. 2025[2026-04-27]. http://arxiv.org/pdf/2502.11054. [8] Zou A, Wang Z, Carlini N, et al. Universal and transferable adversarial attacks on aligned language models [EB/OL]. 2023[2026-04-27]. http://arxiv.org/abs/2307.15043. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||