Protecting Your NLG Models with Semantic and Robust Watermarks

12/10/2021
by   Tao Xiang, et al.
0

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has become a useful tool to protect Intellectual Property (IP) of deep models. However, existing watermarking technologies using backdoors are easily detected or harmful for NLG applications. In this paper, we propose a semantic and robust watermarking scheme for NLG models that utilize unharmful phrase pairs as watermarks for IP protection. The watermarks give NLG models personal preference for some special phrase combinations. Specifically, we generate watermarks by following a semantic combination pattern and systematically augment the watermark corpus to enhance the robustness. Then, we embed these watermarks into an NLG model without misleading its original attention mechanism. We conduct extensive experiments and the results demonstrate the effectiveness, robustness, and undetectability of the proposed scheme.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/16/2021

Protect the Intellectual Property of Dataset against Unauthorized Use

Training high performance Deep Neural Networks (DNNs) models require lar...
research
10/07/2021

Fingerprinting Multi-exit Deep Neural Network Models via Inference Time

Transforming large deep neural network (DNN) models into the multi-exit ...
research
10/03/2022

An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks

Capitalise on deep learning models, offering Natural Language Processing...
research
02/25/2020

Model Watermarking for Image Processing Networks

Deep learning has achieved tremendous success in numerous industrial app...
research
01/21/2021

An Efficient Communication Protocol for FPGA IP Protection

We introduce a protection-based IP security scheme to protect soft and f...
research
10/29/2020

Passport-aware Normalization for Deep Model Protection

Despite tremendous success in many application scenarios, deep learning ...
research
10/22/2019

Towards Combinational Relation Linking over Knowledge Graphs

Given a natural language phrase, relation linking aims to find a relatio...

Please sign up or login with your details

Forgot password? Click here to reset