North Carolina State University, United States
Keywords: Steganography, Cryptography, Cyber-security, Machine Learning.The chemical universe is estimated to be filled with at least 10^60 unique small molecules. As of today, there is no available technology capable of exploiting the chemical space to directly store information in a secure, reproducible, and efficient way. My laboratory at North Carolina State University is developing a new cheminformatics method that directly uses chemical structures and their properties as the central element for securely encoding and storing information. This approach called CryptoChem relies on the Big Chemical Data concept and machine learning. It allows for the encryption of numerical, textual, and imaging data based on series of molecules. This idea of using chemical structures in combination with machine learning for secure storage & exchange of confidential information is fully unique. For instance, Cryptochem can be used for securely exchanging messages worldwide using our dedicated software. Our MOLWRITE and MOLREAD prototype programs can encode and decode data via the use of virtual molecules and deep-learning neural networks. They have been proven to send encrypted messages between two locations with 100% decoding accuracy.