Protect, show, attend and tell: Empowering image captioning models with ownership protection

作者：

Highlights：

• We propose a key-based strategy that provides reliable, preventive and timely IP protection for image captioning task.

• We empirically show the effectiveness of our approach against various attacks and prove the ownership of the model.

• To the best of our knowledge, we are the first to propose IP protection on image captioning model.

摘要

•We propose a key-based strategy that provides reliable, preventive and timely IP protection for image captioning task.•We empirically show the effectiveness of our approach against various attacks and prove the ownership of the model.•To the best of our knowledge, we are the first to propose IP protection on image captioning model.

论文关键词：Image captioning,Ownership protection,Deep neural network,Recurrent neural network,Long short-term memory

论文评审过程：Received 3 April 2021, Revised 16 August 2021, Accepted 28 August 2021, Available online 30 August 2021, Version of Record 5 September 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108285