Demystifying Prompt Stealing Attacks against Synthetic Video
cs.CV, cs.AI, cs.CR
Submitted: 2026-10-26
Updated: 2026-10-26
Comments: 19 pages, 12 figures
Code: https://github.com/openai/CLIP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- ModelScope Text-to-Video Technical Report
- VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
- Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
- VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
- Null-text Inversion for Editing Real Images using Guided Diffusion Models
- Learning Transferable Visual Models From Natural Language Supervision
- Dreamix: Video Diffusion Models are General Video Editors
- Motion-Conditioned Diffusion Model for Controllable Video Synthesis
- Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
- FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
- Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
- Video Diffusion Models: A Survey
- Latent Video Diffusion Models for High-Fidelity Long Video Generation
- SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models
- Prompt Stealing Attacks Against Large Language Models
- SOS! Soft Prompt Attack Against Open-Source Large Language Models
- Denoising Diffusion Implicit Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs