Cryptanalysis of chaos-based image encryption using DL attack

Secure image encryption is necessary to protect our confidential data from malicious access. Chaos-based encryption algorithms have gained significant attention in performing the security of encrypted images because of their complex and random-like behavior. However, the robustness of these encryption schemes against cryptanalysis remains a critical area of research. In this paper, we have designed an innovative deep-learning (DL) method based on the known-plaintext attack (KPA) to focus on the security of chaotic image encryption algorithms. This approach uses a convolutional neural network (CNN) model that has been pre-trained using a set of ciphertext–plaintext pairs to learn chaotic cryptosystem operation mechanisms. Our method is applied to three existing chaotic encryption algorithms. Experimental results show the ability of DL-based models to break different chaotic cryptosystems in contrast to traditional KPA-based cryptanalysis algorithms.