5 papers
LibraGen: Playing a Balance Game in Subject-Driven Video Generation
Jiahao Zhu, Shanshan Lao, Lijie Liu +10
With the advancement of video generation foundation models (VGFMs), customized generation, particularly subject-to-video (S2V), has attracted growing attention. However, a key chal…
Rethinking Security of Diffusion-based Generative Steganography
Jihao Zhu, Zixuan Chen, Jiali Liu +4
Generative image steganography is a technique that conceals secret messages within generated images, without relying on pre-existing cover images. Recently, a number of diffusion m…
SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
Jiahao Zhu, Zixuan Chen, Guangcong Wang +2
Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) t…
Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography
Jiahao Zhu, Zixuan Chen, Jiali Liu +3
Diffusion model-based generative image steganography (DM-GIS) is an emerging paradigm that leverages the generative power of diffusion models to conceal secret messages without req…
3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds
Jiahao Zhu, Huajun Zhou, Zixuan Chen +2
3D deep models consuming point clouds have achieved sound application effects in computer vision. However, recent studies have shown they are vulnerable to 3D adversarial point clo…