Learning to Protect Communications with Adversarial Neural CryptographyDownload PDF

28 Mar 2024 (modified: 22 Oct 2023)Submitted to ICLR 2017Readers: 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 confidentiality goals.
Conflicts: google.com;cmu.edu
TL;DR: Adversarial training of neural networks to learn rudimentary forms of encryption with no pre-specified algorithms
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 5 code implementations](https://www.catalyzex.com/paper/arxiv:1610.06918/code)
12 Replies

Loading