Agentic Copyright Watermarking against Adversarial Evidence Forgery with Purification-Agnostic Curriculum Proxy Learning

arXiv 2409.01541 ↗First posted 3 Sep 2024cs.CV cs.CRcited by 0

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

Abstract (arXiv)

With the proliferation of AI agents in various domains, protecting the ownership of AI models has become crucial due to the significant investment in their development. Unauthorized use and illegal distribution of these models pose serious threats to intellectual property, necessitating effective copyright protection measures. Model watermarking has emerged as a key technique to address this issue, embedding ownership information within models to assert rightful ownership during copyright disputes. This paper presents several contributions to model watermarking: a self-authenticating black-box watermarking protocol using hash techniques, a study on evidence forgery attacks using adversarial perturbations, a proposed defense involving a purification step to counter adversarial attacks, and a purification-agnostic curriculum proxy learning method to enhance watermark robustness and model performance. Experimental results demonstrate the effectiveness of these approaches in improving the security, reliability, and performance of 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 22 of its 34 references that are in the map. First posted on arXiv 3 Sep 2024.

Builds on

22 of 34 references.

References · 22

2017Attention Is All You Needcited by 59,932
2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
2014Explaining and Harnessing Adversarial Examplescited by 7,287
2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
2013Intriguing properties of neural networkscited by 5,114
2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
2015Fast R-CNNcited by 2,930
2016Identity Mappings in Deep Residual Networkscited by 1,960
2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
2017Countering Adversarial Images using Input Transformationscited by 517

10 more

2022Diffusion Models for Adversarial Purificationcited by 469
2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
2021A survey of deep neural network watermarking techniquescited by 69
2020A Systematic Review on Model Watermarking for Neural Networkscited by 49
2018Digital Watermarking for Deep Neural Networkscited by 37

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way