mlsanityData to 7 Oct 2026

A Survey of Fragile Model Watermarking

arXiv 2406.04809 ↗First posted 7 Jun 2024cs.CR cs.AIcited by 1

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

Abstract (arXiv)

Model fragile watermarking, inspired by both the field of adversarial attacks on neural networks and traditional multimedia fragile watermarking, has gradually emerged as a potent tool for detecting tampering, and has witnessed rapid development in recent years. Unlike robust watermarks, which are widely used for identifying model copyrights, fragile watermarks for models are designed to identify whether models have been subjected to unexpected alterations such as backdoors, poisoning, compression, among others. These alterations can pose unknown risks to model users, such as misidentifying stop signs as speed limit signs in classic autonomous driving scenarios. This paper provides an overview of the relevant work in the field of model fragile watermarking since its inception, categorizing them and revealing the developmental trajectory of the field, thus offering a comprehensive survey for future endeavors in model fragile watermarking.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 21 of its 59 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

21 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing11 Apr
  2. 2022Neural network fragile watermarking with no model performance degradation16 Aug

Other references · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  6. 2018Disentangling by Factorisingcited by 614
  7. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  8. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  9. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  10. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  11. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 106
  12. 2021A survey of deep neural network watermarking techniquescited by 69
7 more
  1. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  2. 2017An Entropy-based Pruning Method for CNN Compressioncited by 37
  3. 2021RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recoverycited by 18
  4. 2021Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authenticationcited by 17
  5. 2022PublicCheck: Public Integrity Verification for Services of Run-time Deep Modelscited by 5
  6. 2021DeepiSign: Invisible Fragile Watermark to Protect the Integrityand Authenticity of CNNcited by 4
  7. 2021VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent Diffusioncited by 0