Digital Image Encryption Algorithm Based on Double Chaotic Map and LSTM

In the era of network communication,digital image encryption(DIE)technology is critical to ensure the security of image data.However,there has been limited research on combining deep learning neural networks with chaotic mapping for the encryption of digital images.So,this paper addresses this gap by studying the generation of pseudo-random sequences(PRS)chaotic signals using dual logistic chaotic maps.These signals are then predicted using long and short-term memory(LSTM)networks,resulting in the reconstruction of a new chaotic signal.During the research process,it was discovered that there are numerous training parameters associated with the LSTM network,which can hinder training efficiency.To overcome this challenge and improve training efficiency,the paper proposes an improved particle swarm optimization(IPSO)algorithm to optimize the LSTM network.Subsequently,the obtained chaotic signal from the optimized model training is further scrambled,obfuscated,and diffused to achieve the final encrypted image.This research presents a digital image encryption(DIE)algorithm based on a double chaotic map(DCM)and LSTM.The algorithm demonstrates a high average NPCR(Number of Pixel Change Rate)of 99.56%and a UACI(Unified Average Changing Intensity)value of 33.46%,indicating a strong ability to resist differential attacks.Overall,the proposed algorithm realizes secure and sensitive digital image encryption,ensuring the protection of personal information in the Internet environment.

A conservative chaotic system with coexisting chaotic-like attractors and its application in image encryption

Unlike dissipative systems,conservative systems do not have attractors and no attractor reconstruction occurs.Therefore,these systems are more suitable for application in image encryption.On the basis of above appoints,here we develop and propose a conservative system with infinite chaotic-like attractors.The conservative and chaotic characteristics and coexistence chaotic-like attractors are studied using Lyapunov exponents,Poincare maps,and numerical simulation.The results show that the coexistence of chaotic-like attractors has a more complex structure and dynamic behaviour than traditional ones.Additionally,the developed system is further used to design an encryption system for a digital image.Using the coexistence chaotic-like attractor sequence to scramble and diffuse the image can destroy the correlation of adjacent pixels and hide the information of all pixels.The feasibility and security of the encryption scheme are demonstrated through the analysis of key space,histogram,information entropy,key sensitivity and pixel correlation.