Du X, Mo F, Wen M, Gu T, Zheng H, Jin H, Shi J. Multi-Turn Jailbreaking Large Language Models via Attention Shifting. AAAI [Internet]. 2025Apr.11 [cited 2026May3];39(22):23814-22. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34553