Holograms are being used to encode information, which can only be unlocked by special neural networks, opening the way for a new level of data security.
Researchers from the Institute of Electronic Structure and Laser, in Greece, say the new encryption system uses a unique neural network to generate a decryption key to unlock the hologram.
Research team leader Stelios Tzortzakis said the discovery could pave the way for more secure communication channels, helping to protect sensitive data.
“From rapidly evolving digital currencies to governance, healthcare, communications and social networks, the demand for robust protection systems to combat digital fraud continues to grow,” Professor Tzortzakis said.
“Our new system achieves an exceptional level of encryption by utilizing a neural network to generate the decryption key, which can only be created by the owner of the encryption system.”
He said the new system used the neural networks to retrieve elaborately scrambled information stored as a hologram.
Professor Tzortzakis said the study showed that trained neural networks could successfully decode the intricate spatial information in the scrambled images.
“Our study provides a strong foundation for many applications, especially cryptography and secure wireless optical communication, paving the way for next-generation telecommunication technologies.
“The method we developed is highly reliable even in harsh and unpredictable conditions, addressing real-world challenges like tough weather that often limit the performance of free-space optical systems.”
Professor Tzortzakis said the researchers developed the new system after discovering that when holograms were used to encode a laser beam, the beam would become completely and randomly scrambled and that the original beam shape could not be recognized or retrieved using physical analysis or calculation.
“The challenge was figuring out how to decrypt the information,” he said.
“We came up with the idea of training neural networks to recognize the incredibly fine details of the scrambled light patterns.
“By creating billions of complex connections, or synapses, within the neural networks, we were able to reconstruct the original light beam shapes. This meant we had a way to create the decryption key that was specific for each encryption system configuration.”
Read the full study: Encrypted optical information in nonlinear chaotic systems uncovered using neural networks.