作者位次 #7/9AAAI 2026Poster· Artificial Intelligence
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Shuhan Xu · Siyuan Liang · Hongling Zheng · Aishan Liu · Xinbiao Wang · Yong Luo · Fu Lin · Leszek Rutkowski · Dacheng Tao