Deep-Lock: Secure Authorization for Deep Neural Networks

Stealing machine learning models via prediction apis. In 25th USENIX Security Symposium (USENIX Security 16) . 601–618

Florian Tramèr, Fan Zhang, Ari Juels, Michael K Reiter, and Thomas Ristenpart. 2016 · 2016

Earlier work this paper cites.

Turning your weakness into a strength: Watermarking deep neural networks by backdooring. In 27th USENIX Security Symposium (USENIX Security 18) . 1615–1631

Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, and Joseph Keshet. 2018 · 2018

Earlier work this paper cites.

Watermarking deep neural networks for embedded systems. In 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) . IEEE, 1–8

Jia Guo and Miodrag Potkonjak. 2018 · 2018

Earlier work this paper cites.

Deepobfuscation: Securing the structure of convolutional neural networks via knowledge distillation

Original

Hui Xu, Yuxin Su, Zirui Zhao, Yangfan Zhou, Michael R Lyu, and Irwin King. 2018 · 2018

Cited alongside, same era.

DeepSigns: an end-to-end watermarking framework for ownership protection of deep neural networks. In Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems . 485–497

Bita Darvish Rouhani, Huili Chen, and Farinaz Koushanfar. 2019 · 2019

Cited alongside, same era.

Hardware-Assisted Intellectual Property Protection of Deep Learning Models. In Proceedings of the 57th Annual Design Automation Conference 2020

Abhishek Chakraborty, , Ankit Mondal, and Ankur Srivastava. 2020 · 2020

Cited alongside, same era.

Cloudleak: Large-scale deep learning models stealing through adversarial examples. In Proceedings of Network and Distributed Systems Security Symposium

Honggang Yu, Kaichen Yang, Teng Zhang, Yun-Yun Tsai, Tsung-Yi Ho, and Yier Jin. 2020 · 2020

Closest in time.

NN-Lock: A Lightweight Authorization to Prevent IP Threats of Deep Learning Models

Manaar Alam, Sayandeep Saha, Debdeep Mukhopadhyay, and Sandip Kundu. 2022 · 2022

Closest in time.