Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking

Researchers have developed a new white-box watermarking framework that uses chaotic sequences to embed ownership information into deep neural network parameters for intellectual property protection. The method uses logistic maps and genetic algorithms to verify model ownership without degrading performance, showing effectiveness on MNIST and CIFAR-10 datasets.

• →New watermarking technique embeds ownership information into DNN weights using chaos-based sequences without structural model modifications.
• →The method uses logistic maps to generate chaotic sequences and genetic algorithms for ownership verification.
• →Watermarks remain detectable after model fine-tuning with negligible impact on accuracy.
• →Testing on MNIST and CIFAR-10 datasets demonstrates the framework's effectiveness for IP protection.
• →The solution addresses growing concerns about DNN intellectual property theft and unauthorized model redistribution.