Epistemology

Machine learning

Digital watermarking

Task (project management)

Deep neural networks

Engineering

Philosophy

Artificial intelligence

Deep learning

Image (mathematics)

Political science

Systems engineering

Operating system

Property (philosophy)

Computer science

Variety (cybernetics)

Key (lock)

Intellectual property

Harm

Computer security

Artificial neural network

Deep learning technologies, which are the key components of state-of-the-art Artificial Intelligence (AI) services, have shown great success in providing human-level capabilities for a variety of tasks, such as visual analysis, speech recognition, and natural language processing and etc. Building a production-level deep learning model is a non-trivial task, which requires a large amount of training data, powerful computing resources, and human expertises. Therefore, illegitimate reproducing, distribution, and the derivation of proprietary deep learning models can lead to copyright infringement and economic harm to model creators. Therefore, it is essential to devise a technique to protect the intellectual property of deep learning models and enable external verification of the model ownership.

Protecting Intellectual Property of Deep Neural Networks with Watermarking