Crypt | 2019
Sharing data securely is one of the biggest roadblocks in the implementation of artificial intelligence(AI) solutions. Intelligence can be accomplished only with very large datasets, which are required to train the networks. Sharing of this data anonymously and securely is a huge issue, with brute force attacks and data breaches becoming increasingly common. As a result, companies tend to be incredibly protective of their data assets and very conservative when comes to share them with other people. At the same token, data scientists need access to large labeled datasets in order to validate their models.
Neural Cryptography is the training of neural networks to discover forms of encryption and decryption, without being taught specific algorithms for these purposes. Neural networks can learn to protect the confidentiality of their data from other neural networks.
Cryptography involving Symmetric encryption uses the same key for both encryption and decryption. Cryptography implementing neural networks attempts to improve security by complicating attacks. Neural networks can communicate discreetly with each other without using the conventional cryptography algorithms. This is done using end to end adversarial training( attempting to attack the communication) to ensure security.