# VideoEraser: Concept Erasure in Text-to-Video Diffusion Models

arXiv: https://arxiv.org/abs/2508.15314 · HTML: https://mlsanity.com/paper/2508.15314/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 23 of its 60 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [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)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models](https://mlsanity.com/paper/2407.05965/) (2024)
- [IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI](https://mlsanity.com/paper/2310.19248/) (2023)
- [SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset](https://mlsanity.com/paper/2406.14477/) (2024)
- [Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning](https://mlsanity.com/paper/2405.07288/) (2024)
- [Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends](https://mlsanity.com/paper/2508.11548/) (2025)

## Built on by (most cited first, 14 of 14)

- [CGCE: Classifier-Guided Concept Erasure in Generative Models](https://mlsanity.com/paper/2511.05865/) (2025)
- [EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization](https://mlsanity.com/paper/2603.00978/) (2026)
- [PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models](https://mlsanity.com/paper/2603.21547/) (2026)
- [Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation](https://mlsanity.com/paper/2604.10071/) (2026)
- [ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2605.05938/) (2026)
- [Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2605.25941/) (2026)
- [Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2607.25366/) (2026)
- [FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning](https://mlsanity.com/paper/2610.03980/) (2026)
- [Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2610.05601/) (2026)
- [Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models](https://mlsanity.com/paper/2607.14194/) (2026)
- [Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition](https://mlsanity.com/paper/2607.14521/) (2026)
- [CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2609.20267/) (2026)
- [Motion Concept Unlearning in Video Diffusion Models](https://mlsanity.com/paper/2609.36832/) (2026)
- [FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning](https://mlsanity.com/paper/2609.39605/) (2026)

## Abstract (arXiv)

The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous datasets, including unauthorized personal identities, artistic creations, and harmful materials, which can lead to uncontrolled production and distribution of such content. To address this, we propose VideoEraser, a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts, even when explicitly prompted with those concepts. Designed as a plug-and-play module, VideoEraser can seamlessly integrate with representative T2V diffusion models via a two-stage process: Selective Prompt Embedding Adjustment (SPEA) and Adversarial-Resilient Noise Guidance (ARNG). We conduct extensive evaluations across four tasks, including object erasure, artistic style erasure, celebrity erasure, and explicit content erasure. Experimental results show that VideoEraser consistently outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability. Notably, VideoEraser achieves state-of-the-art performance in suppressing undesirable content during T2V generation, reducing it by 46% on average across four tasks compared to baselines.