Protecting the Intellectual Property of AI with Watermarking

phys.org | 7/20/2018 | Staff
chrismpotts (Posted by) Level 3
Click For Photo: https://3c1703fe8d.site.internapcdn.net/newman/gfx/news/2018/1-protectingth.jpg

If we can protect videos, audio and photos with digital watermarking, why not AI models?

This is the question my colleagues and I asked ourselves as we looked to develop a technique to assure developers that their hard work in building AI, such as deep learning models, can be protected. You may be thinking, "Protected from what?" Well, for example, what if your AI model is stolen or misused for nefarious purposes, such as offering a plagiarized service built on stolen model? This is an concern, particularly for AI leaders such as IBM.

Month - Research - AsiaCCS - '18 - Conference

Earlier this month we presented our research at the AsiaCCS '18 conference in Incheon, Republic of Korea, and we are proud to say that our comprehensive evaluation technique to address this challenge was demonstrated to be highly effective and robust. Our key innovation is that our concept can remotely verify the ownership of deep neural network (DNN) services using simple API queries.

As deep learning models are more widely deployed and become more valuable, they are increasingly targeted by adversaries. Our idea, which is patent-pending, takes inspiration from the popular watermarking techniques used for multimedia content, such as videos and photos.

Photo - Stages - Embedding - Detection - Embedding

When watermarking a photo there are two stages: embedding and detection. In the embedding stage, owners can overlay the word "COPYRIGHT" on the photo (or watermarks invisible to human perception) and if it's stolen and used by others we confirm this in the detection stage, whereby owners can extract the watermarks as legal evidence to prove ownership. The same idea can be applied to DNN.

By embedding watermarks to DNN models, if they are stolen, we can verify the ownership by extracting watermarks from the models. However, different from digital watermarking, which embeds watermarks into multimedia content, we needed to design a new method to embed watermarks into DNN models.

In our...
(Excerpt) Read more at: phys.org
Wake Up To Breaking News!
Sometimes I Wake Up Grumpy. Other Times I Let Her Sleep
Tagged:
Sign In or Register to comment.

Welcome to Long Room!

Where The World Finds Its News!