HAO, Haojie; WANG, Jiakai; LIU, Aishan; MA, Yuqing; QIN, Haotong; GUO, Yuanfang; LIU, Xianglong. Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 42, p. 35481–35489, 2026. DOI: 10.1609/aaai.v40i42.40858. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40858. Acesso em: 15 may. 2026.