mlsanityData to 14 Oct 2026

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs

arXiv 2407.02411 ↗First posted 2 Jul 2024cs.CV cs.CR cs.MMcited by 7

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, even without authorization. This paper introduces Video Watermarking, a novel technique to protect videos from unauthorized annotations by such video-based LLMs, especially concerning the video content and description, in response to specific queries. By imperceptibly embedding watermarks into key video frames with multi-modal flow-based losses, our method preserves the viewing experience while preventing misuse by video-based LLMs. Extensive experiments show that Video Watermarking significantly reduces the comprehensibility of videos with various video-based LLMs, demonstrating both stealth and robustness. In essence, our method provides a solution for securing video content, ensuring its integrity and confidentiality in the face of evolving video-based LLMs technologies.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 45 of its 63 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

45 of 63 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  8. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  9. 2023VideoChat: Chat-Centric Video Understandingcited by 857
  10. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
  11. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 501
  12. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Promptscited by 398
33 more
  1. 2020Multi-modal Transformer for Video Retrievalcited by 395
  2. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 393
  3. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
  4. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 314
  5. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 284
  6. 2021Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptionscited by 226
  7. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 167
  8. 2015Sequence to Sequence -- Video to Textcited by 158
  9. 2022End-to-end Generative Pretraining for Multimodal Video Captioningcited by 116
  10. 2023BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learningcited by 115
  11. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  12. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  13. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  14. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 76
  15. 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagescited by 69
  16. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 67
  17. 2023MagicStick: Controllable Video Editing via Control Handle Transformationscited by 62
  18. 2019Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioningcited by 60
  19. 2018Sparse Adversarial Perturbations for Videoscited by 57
  20. 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
  21. 2021Open-book Video Captioning with Retrieve-Copy-Generate Networkcited by 43
  22. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 40
  23. 2020Improving Query Efficiency of Black-box Adversarial Attackcited by 34
  24. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  25. 2024Adversarial Robustness for Visual Grounding of Multimodal Large Language Modelscited by 23
  26. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  27. 2022SimVTP: Simple Video Text Pre-training with Masked Autoencoderscited by 21
  28. 2024Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Modelscited by 17
  29. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  30. 2024FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMscited by 14
  31. 2024Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samplescited by 14
  32. 2024Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Maskcited by 5
  33. 2024Genos: General In-Network Unsupervised Intrusion Detection by Rule Extractioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 36
  2. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  3. 2025Protecting Your Video Content: Disrupting Automated Video-based LLM Annotationscited by 5
  4. 2025VideoGuard: Protecting Video Content from Unauthorized Editingcited by 3
  5. 2025Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Modelscited by 2
  6. 2025FeatureFool: Zero-Query Fooling of Video Models via Feature Mapcited by 0
  7. 2026It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at ε≤ 4/255cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Watermarking Techniques for Large Language Models: A Survey
  2. 2024No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
  3. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challenges
  4. 2024Video Seal: Open and Efficient Video Watermarking
  5. 2023Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
  6. 2024Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
  7. 2025VideoMarkBench: Benchmarking Robustness of Video Watermarking
  8. 2024LVMark: Robust Watermark for Latent Video Diffusion Models