Author

Wei Lu

h-index 9 View on Semantic Scholar

We have 2 of 40 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models

I2VShield is proposed, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models that achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, wh...

Yi-Mao Guo, Zuo-Min Qu, Wei Lu · arXiv.org · 0 citations

Jul 2026

HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales

The introduction of HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery benchmark containing over 18,000 synthesized videos across four distinct scenarios, and the proposed Gen2Anno (Generation-to-Annotation), a cooperative multi-agent pipeline that generates logically grounded forensic r...

Wenbo Xu, Zhimin Chen, Xiaojie Liang et al. · arXiv.org · 0 citations