# LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse

arXiv: https://arxiv.org/abs/2610.13333 · HTML: https://mlsanity.com/paper/2610.13333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 34)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples](https://mlsanity.com/paper/2302.04578/) (2023)
- [Raising the Cost of Malicious AI-Powered Image Editing](https://mlsanity.com/paper/2302.06588/) (2023)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [Anti-DreamBooth: Protecting users from personalized text-to-image synthesis](https://mlsanity.com/paper/2303.15433/) (2023)
- [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://mlsanity.com/paper/2303.14717/) (2023)
- [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [Toward effective protection against diffusion based mimicry through score distillation](https://mlsanity.com/paper/2311.12832/) (2023)
- [Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?](https://mlsanity.com/paper/2312.00084/) (2023)
- [IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI](https://mlsanity.com/paper/2310.19248/) (2023)
- [AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset](https://mlsanity.com/paper/2503.19462/) (2025)
- [Dormant: Defending against Pose-driven Human Image Animation](https://mlsanity.com/paper/2409.14424/) (2024)
- [StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations](https://mlsanity.com/paper/2505.18766/) (2025)
- [Anti-I2V: Safeguarding your photos from malicious image-to-video generation](https://mlsanity.com/paper/2603.24570/) (2026)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Video Deepfake Abuse: How Company Choices Predictably Shape Misuse Patterns](https://mlsanity.com/paper/2512.11815/) (2025)
- [Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization](https://mlsanity.com/paper/2607.13336/) (2026)
- [Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation](https://mlsanity.com/paper/2604.10837/) (2026)

## Abstract (arXiv)

Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos, posing threats of misuse as anyone can turn personal photos into fabricated videos without consent. A promising solution is to proactively add an adversarial perturbation to the image before release, such that videos generated from it would be unfaithful or visually corrupted. However, due to an insufficient understanding of what governs how subsequent frames read the reference image in modern I2V models, existing protections struggle to offer strong protection under common perturbation budgets. In this paper, we approach the problem by exploring this underlying reading mechanism. Through a convex geometric analysis, we theoretically identify the spread of the reference value vectors as a key factor governing this reading process, and empirically find that even a mild contraction of this spread can severely degrade the generated video, making it an efficient lever for protection. Guided by this insight, we propose LETHE, a novel protection method that directly disrupts this reading process. LETHE pairs two complementary objectives, where a value collapse objective drives the reference value vectors toward uniformity, while an attention attraction objective draws subsequent frames toward these collapsed tokens to amplify corruption. We further construct two human-centric I2V protection benchmarks and conduct extensive experiments with multiple modern I2V models, which demonstrate the state-of-the-art protection performance and versatility of LETHE.