KVeil: First-Place Solution to ECCV 2026 LifeGenIP Challenge on Unlearnable Videos

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: Technical report for the winning solution (1st place, both phases) of the ECCV 2026 LifeGenIP Challenge on Unlearnable Videos against Diffusion-based Customization

Code: https://github.com/AntigoneRandy/KVeil

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
• Sample and Computation Redistribution for Efficient Face Detection
• I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• LoRA: Low-Rank Adaptation of Large Language Models
• Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
• Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
• VGMShield: Mitigating Misuse of Video Generative Models
• Seedance 2.0: Advancing Video Generation for World Complexity
• Anti-I2V: Safeguarding your photos from malicious image-to-video generation
• Wan: Open and Advanced Large-Scale Video Generative Models
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

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