Transformers -- Messages in Disguise
Joshua H. Tyler, Mohamed K.M. Fadul, Donald R. Reising

TL;DR
This paper introduces a novel neural network-based cryptography scheme called RANDOM ANC, which is efficient, unique, and communication overhead-free, potentially revolutionizing adaptive encryption methods.
Contribution
The paper presents the RANDOM ANC model with three new neural network layers, enabling efficient, key-specific encryption without additional communication overhead.
Findings
RANDOM ANC achieves up to 2.5 MB/sec encryption speed.
The model requires only 100 KB storage.
It ensures message uniqueness tied to encryption keys.
Abstract
Modern cryptography, such as Rivest Shamir Adleman (RSA) and Secure Hash Algorithm (SHA), has been designed by humans based on our understanding of cryptographic methods. Neural Network (NN) based cryptography is being investigated due to its ability to learn and implement random cryptographic schemes that may be harder to decipher than human-designed algorithms. NN based cryptography may create a new cryptographic scheme that is NN specific and that changes every time the NN is (re)trained. This is attractive since it would require an adversary to restart its process(es) to learn or break the cryptographic scheme every time the NN is (re)trained. Current challenges facing NN-based encryption include additional communication overhead due to encoding to correct bit errors, quantizing the continuous-valued output of the NN, and enabling One-Time-Pad encryption. With this in mind, the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications
