Learning to Protect Communications with Adversarial Neural Cryptography

Code

• github.com/mguarin0/LearningToProtectCommunicationsWithAdversarialNeuralCryptography
  pytorch★ 11
• github.com/Agwave/Pytorch-Adversarial-Neural-Cryptography
  pytorch★ 8
• github.com/avani17101/Adversarial-Neural-Crypto
  none★ 0
• github.com/asya-b/adversarial-cnn-cryptography
  tf★ 0
• github.com/tensorflow/models/tree/master/research/adversarial_crypto
  tf★ 0
• github.com/EXYNOS-999/MIT_utrc
  none★ 0
• github.com/marcellodebernardi/adversarial-csprng
  tf★ 0
• github.com/IBM/MAX-Adversarial-Cryptography
  tf★ 0
• github.com/Rutts07/Adversarial-Neural-Crytography
  pytorch★ 0

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.

Reproductions