2 papers
cs.CV2026
CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models
Shuhan Xu, Siyuan Liang, Hongling Zheng +4
Diffusion-based image-to-video (I2V) models increasingly exhibit world-model-like properties by implicitly capturing temporal dynamics. However, existing studies have mainly focuse…
cs.CV2025
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Shuhan Xu, Siyuan Liang, Hongling Zheng +6
Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject…