Overview:
Machine learning techniques, especially deep learning (DL) techniques, have made significant technological break-throughs in recent years and are widely applied in many fields, such as image classification, object detection, voice recognition, natural language processing, self-driving cars, smart healthcare, etc. Trained DL models are of high value and must be considered intellectual property of the legitimate owner, i.e. the party that created it. The value of DL models lies in the effort and resources allocated in the process of training data collection, cleansing, pre-processing, organizing, storing, and in certain cases even manual labelling, which is often time-consuming and expensive. Therefore, there is an urgent need to protect deep learning (DL) models from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. This workshop is intended to be positioned at the frontier of IPR protection research [1-4] and showcase the most excellent and advanced work underway at academic and private research organizations as well as government labs.

References:

1. DeepIP: Deep Neural Network Intellectual Property Protection with Passports, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
2. Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attacks, CVPR 2021
3. Embedding Watermarks into Deep Neural Networks, ICMR 2017.
4. Protecting Intellectual Property of Deep Neural Networks with Watermarking, ASIACCS, 2018

Call for Papers:
We welcome submissions on theory and applications of Intellectual Property Protection (IPR) with a strong emphasis on the protection of Deep Learning models as services. All accepted papers will be presented at the poster sessions. A subset of accepted submissions will also have oral presenta-tions. At least one author of each accepted paper is expected to represent it at the workshop. Topics including (but not limit to):

• Watermarking for Deep Learning Models
• Watermarking for Ownership Verifications
• Cryptography
• Protocol and Regulation for Deep Learning Models Ownership Protection

Submission Instructions:
Submissions should be a maximum of 6 pages (not including the list of references). We do accept submissions of work recently published or currently under review. The submissions can contain author details. The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have their work published on the workshop webpage. Please refer this formatting guidelines, LaTeX styles, and Word template for submission.

Submission Deadline: 15 July 2021
Submission Site = CMT Submisison Site