Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning to Protect Communications with Adversarial Neural Cryptography
Martín Abadi, David G. Andersen
Oct 21, 2016 (modified: Oct 21, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:We ask whether neural networks can learn to use secret keys to protect
information from other neural networks. Specifically, we focus on
ensuring confidentiality properties in a multiagent system, and we
specify those properties in terms of an adversary. Thus, a
system may consist of neural networks named Alice and Bob, and we aim
to limit what a third neural network named Eve learns from
eavesdropping on the communication between Alice and Bob.
We do not prescribe specific cryptographic algorithms to these neural networks;
instead, we train end-to-end, adversarially.
We demonstrate that the neural networks can learn
how to perform forms of encryption and decryption, and also
how to apply these operations selectively in order to meet
TL;DR:Adversarial training of neural networks to learn rudimentary forms of encryption with no pre-specified algorithms
Enter your feedback below and we'll get back to you as soon as possible.