mlsanityData to 14 Oct 2026

Trigger-Based Fragile Model Watermarking for Image Transformation Networks

arXiv 2409.19442 ↗First posted 28 Sep 2024cs.CRcited by 0

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

Abstract (arXiv)

In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile watermarking for model integrity has been studied in classification models, image transformation/generation models have yet to be explored. We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks that takes advantage of properties inherent to image outputs. For example, manifesting watermarks as specific visual patterns, styles, or anomalies in the generated content when particular trigger inputs are used. Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks, outperforming baselines by 94%. We conduct additional experiments to analyze the security of this approach, the flexibility of the trigger and resulting watermark, and the sensitivity of the watermarking loss on performance. We also demonstrate the applicability of this approach on two different tasks (1 immediate task and 1 downstream task). This is the first work to consider fragile model watermarking for image transformation/generation networks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 23 of its 60 references that are in the map. First posted on arXiv 28 Sep 2024.

Builds on

23 of 60 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Protecting Language Generation Models via Invisible Watermarking6 Feb
  2. 2023A Watermark for Large Language Models24 Jan
  3. 2022CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks19 Sep
  4. 2022Neural network fragile watermarking with no model performance degradation16 Aug

Other references · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  4. 2020Backdoor Learning: A Surveycited by 426
  5. 2019Hidden Trigger Backdoor Attackscited by 371
  6. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  7. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  8. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  10. 2021Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratchcited by 102
  11. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 86
  12. 2021Handcrafted Backdoors in Deep Neural Networkscited by 63
7 more
  1. 2020Model Watermarking for Image Processing Networkscited by 56
  2. 2020A Systematic Review on Model Watermarking for Neural Networkscited by 52
  3. 2018Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detectioncited by 47
  4. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 41
  5. 2022Marksman Backdoor: Backdoor Attacks with Arbitrary Target Classcited by 33
  6. 2022Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removalcited by 20
  7. 2022Deep Fidelity in DNN Watermarking: A Study of Backdoor Watermarking for Classification Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing
  2. 2024A Survey of Fragile Model Watermarking
  3. 2023Decision-based iterative fragile watermarking for model integrity verification
  4. 2024RoboSignature: Robust Signature and Watermarking on Network Attacks
  5. 2024Probabilistically Robust Watermarking of Neural Networks
  6. 2026Persistent Watermarking of Text-to-Image Models
  7. 2021Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks
  8. 2026One Prompt Is Enough: Watermark Laundering Through Foundation Image Models