3 papers
cs.CV2026
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
Haiquan Wen, Yiwei He, Zhenglin Huang +7
As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal…
cs.CV2026
Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens
Zhiwen Zheng, Yuheng Qiao, Xiaoshuai Zhang +7
Noncontact exfiltration of electronic screen content poses a security challenge, with side-channel incursions as the principal vector. We introduce an optical projection side-chann…
cs.CV2025
Wavefront-Constrained Passive Obscured Object Detection
Zhiwen Zheng, Yiwei Ouyang, Zhao Huang +7
Accurately localizing and segmenting obscured objects from faint light patterns beyond the field of view is highly challenging due to multiple scattering and medium-induced perturb…