LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse
cs.CV, cs.CR
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: Preprint, under review
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- A Short Note on the Kinetics-700 Human Action Dataset
- LTX-Video: Realtime Video Latent Diffusion
- Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
- Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns
- Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation
- VGMShield: Mitigating Misuse of Video Generative Models
- Raising the Cost of Malicious AI-Powered Image Editing
- Efficient Video Diffusion Models: Advancements and Challenges
- Intriguing properties of neural networks
- Anti-I2V: Safeguarding your photos from malicious image-to-video generation
- Wan: Open and Advanced Large-Scale Video Generative Models
- Image-to-Video Diffusion: From Foundations to Open Frontiers
- Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
- AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
- Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models