Hao H, Wang J, Liu A, Ma Y, Qin H, Guo Y, et al. Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 15];40(42):35481-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40858