Zhu L, Ning R, Li J, Xin C, Wu H. SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly. AAAI [Internet]. 2024 Mar. 24 [cited 2026 May 9];38(7):7766-74. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/28611