ML Model Watermarking

Protect your machine learning models easily and securely with watermarking

Reference

1. [ICDE’ 22] Identification for Deep Neural Network:Simply Adjusting Few Weights!
   paper
2. [AAAI’ 22] Cosine model watermark against ensemble distillation
   paper
3. [WWW’ 21] [RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks]
   paper | code
4. [ICML’ 21] Watermarking Deep Neural Networks with Greedy Residuals
   paper | code
5. [ICCV’ 23] Towards Robust Model Watermark via Reducing Parametric Vulnerability
   paper
6. [IJCAI’ 22] MetaFinger: Fingerprinting the Deep Neural Networks with Meta-training
   paper
7. [AAAI’ 22] DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding
   paper
8. [AAAI’ 22] Defending against Model Stealing via Verifying Embedded External Features
   paper | code
9. [USENIX’ 21] Entangled Watermarks as a Defense against Model Extraction
   paper | code
10. [ICASSP’ 22] Encryption Resistant Deep Neural Network Watermarking
    paper
11. [ICML' 22] Certified Neural Network Watermarks with Randomized Smoothing
    paper | code
12. [NIPS' 22] Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
    paper | code
13. [CVPR' 22] Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
    paper
14. [KDD' 22] MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprinting
    paper