Enhancing Quantum Image Encryption With QLSTM and Chaos Synchronisation Control: A Deep Neural Network Approach

Quantum image encryption is crucial for data protection, but current methods lack attack resistance and have complex encryption processes. This paper proposes a quantum long short - term memory (QLSTM)-based quantum image encryption method to enhance chaotic sequences and achieve chaos synchronisation control. The QLSTM network improves the Lorenz chaotic sequence, increasing its unpredictability. An adaptive synchronisation control algorithm, using the enhanced chaotic sequence from QLSTM, ensures sender-receiver synchronization. Optimised through deep neural networks, the system maintains stable synchronization under interference. New cryptographic quantum infrastructure (NCQI) was constructed, and images were encrypted using third-order radial diffusion, quantum generalised Arnold transform, and quantum W transform. The QLSTM-improved chaotic sequence showed excellent LLE and 0–1 test results. Information entropy was near 8, with R, G and B channels exceeding 7.999. Anti-attack analysis revealed high information entropy, strong attack resistance, and number of pixels change rate/unified average changing intensity (NPCR/UACI) values of 99.698% and 33.460%, respectively, indicating significant pixel-level changes. Combining quantum chaotic system prediction with the QLSTM model enhanced quantum communication stability and anti-interference ability. This QLSTM-based quantum encryption method, with chaos synchronisation control, significantly improves encryption security and reliability, maintaining high information entropy and complexity under attacks, proving its effectiveness in image encryption.