Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies

Concrete problems in ai safety

Original

Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mané · 2016

Earlier work this paper cites.

Stealing machine learning models via prediction apis

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

Earlier work this paper cites.

Digital watermarking and steganography: fundamentals and techniques

Frank Y Shih · 2017

Cited alongside, same era.

Embedding watermarks into deep neural networks

Yusuke Uchida, Yuki Nagai, Shigeyuki Sakazawa, and Shin’ichi Satoh · 2017

Cited alongside, same era.

The faults in our pi stars: Security issues and open challenges in deep reinforcement learning

Original

Vahid Behzadan and Arslan Munir · 2018

Later among the works it cites.

Detecting backdoor attacks on deep neural networks by activation clustering

Original

Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy, and Biplav Srivastava · 2018

Later among the works it cites.