mlsanityData to 7 Oct 2026

RandMark: On Random Watermarking of Visual Foundation Models

arXiv 2603.10695 ↗First posted 11 Mar 2026cs.CV cs.AIcited by 0

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

Abstract (arXiv)

Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer vision tasks. The high computational cost of data collection and training makes these models valuable assets, which motivates some VFM owners to distribute them alongside a license to protect their intellectual property rights. In this paper, we propose an approach to ownership verification of visual foundation models that leverages a small encoder-decoder network to embed digital watermarks into an internal representation of a hold-out set of input images. The method is based on random watermark embedding, which makes the watermark statistics detectable in functional copies of the watermarked model. Both theoretically and experimentally, we demonstrate that the proposed method yields a low probability of false detection for non-watermarked models and a low probability of false misdetection for watermarked models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 17 of its 27 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

17 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Watermarking Makes Language Models Radioactive22 Feb

Other references · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  10. 2023A Cookbook of Self-Supervised Learningcited by 248
  11. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  12. 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 68
4 more
  1. 2021Defending against Model Stealing via Verifying Embedded External Featurescited by 44
  2. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 39
  3. 2024ManiFPT: Defining and Analyzing Fingerprints of Generative Modelscited by 18
  4. 2024Probabilistically Robust Watermarking of Neural Networkscited by 7

Built on by

Not cited yet.