"An Uncrackable Combination of Invisible Ink and Artificial Intelligence"

Although electronic records continue to advance, paper is still a common method of preserving data. Invisible ink can be used to hide classified economic, commercial, or military information, but many popular inks have toxic compounds or can be seen with predictable methods like chemicals, light, or heat. Carbon nanoparticles, which are low in toxicity, can be invisible under ambient lighting but can create vibrant images when exposed to ultraviolet (UV) light. Advances in Artificial Intelligence (AI) models can ensure that messages can only be deciphered on properly trained computers. A team of researchers trained an AI model to identify and decrypt symbols printed in a fluorescent carbon nanoparticle ink that reveal hidden messages when exposed to UV light. They taught the AI model, made up of multiple algorithms, to recognize the symbols illuminated by UV light and decode them through the use of a special code book. Then they tested whether the AI model can decode messages printed using a combination of regular red ink and the UV fluorescent ink. The AI model read the regular ink symbols as "STOP," with 100% accuracy. When a UV light illuminated the writing, the invisible ink showed the desired message "BEGIN." According to the researchers, since these algorithms can notice modifications in symbols, this approach has the potential to encrypt messages securely using hundreds of different unpredictable symbols. This article continues to discuss the approach to improving paper information recording and security protection using invisible ink and AI. 

Science Daily reports "An Uncrackable Combination of Invisible Ink and Artificial Intelligence"