mlsanityData to 14 Oct 2026

ClearMark: Intuitive and Robust Model Watermarking via Transposed Model Training

arXiv 2310.16453 ↗First posted 25 Oct 2023cs.LGcited by 0

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

Abstract (arXiv)

Due to costly efforts during data acquisition and model training, Deep Neural Networks (DNNs) belong to the intellectual property of the model creator. Hence, unauthorized use, theft, or modification may lead to legal repercussions. Existing DNN watermarking methods for ownership proof are often non-intuitive, embed human-invisible marks, require trust in algorithmic assessment that lacks human-understandable attributes, and rely on rigid thresholds, making it susceptible to failure in cases of partial watermark erasure. This paper introduces ClearMark, the first DNN watermarking method designed for intuitive human assessment. ClearMark embeds visible watermarks, enabling human decision-making without rigid value thresholds while allowing technology-assisted evaluations. ClearMark defines a transposed model architecture allowing to use of the model in a backward fashion to interwove the watermark with the main task within all model parameters. Compared to existing watermarking methods, ClearMark produces visual watermarks that are easy for humans to understand without requiring complex verification algorithms or strict thresholds. The watermark is embedded within all model parameters and entangled with the main task, exhibiting superior robustness. It shows an 8,544-bit watermark capacity comparable to the strongest existing work. Crucially, ClearMark's effectiveness is model and dataset-agnostic, and resilient against adversarial model manipulations, as demonstrated in a comprehensive study performed with four datasets and seven architectures.

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 24 of its 70 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

24 of 70 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models10 Dec

Other references · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  7. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  8. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  10. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 231
  11. 2017Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?cited by 221
  12. 2020Entangled Watermarks as a Defense against Model Extractioncited by 149
11 more
  1. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 118
  2. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
  3. 2021A survey of deep neural network watermarking techniquescited by 73
  4. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 66
  5. 2020Model Watermarking for Image Processing Networkscited by 56
  6. 2020A Systematic Review on Model Watermarking for Neural Networkscited by 52
  7. 2020Spread-Transform Dither Modulation Watermarking of Deep Neural Networkcited by 26
  8. 2020Removing Backdoor-Based Watermarks in Neural Networks with Limited Datacited by 25
  9. 2021Teacher Model Fingerprinting Attacks Against Transfer Learningcited by 16
  10. 2017Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimizationcited by 8
  11. 2019TamperNN: Efficient Tampering Detection of Deployed Neural Netscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Deep Model Intellectual Property Protection via Deep Watermarking
  2. 2023Towards Robust Model Watermark via Reducing Parametric Vulnerability
  3. 2024FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks
  4. 2023On Function-Coupled Watermarks for Deep Neural Networks
  5. 2025Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation
  6. 2022Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networks
  7. 2021Ownership Verification of DNN Architectures via Hardware Cache Side Channels
  8. 2023Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation