Image encryption scheme based on alternate quantum walks and discrete cosine transform

Medical image diagnosis based on adaptive Hybrid Quantum CNN

Hybrid quantum systems have shown promise in image classification by combining the strengths of both classical and quantum algorithms. These systems leverage the parallel processing power of quantum computers to perform complex computations while utilizing classical algorithms to handle the vast amounts of data involved in imaging. The hybrid approach is intended to improve accuracy and speed compared to traditional classical methods. Further research and development in this area can revolutionize the way medical images are classified and help improve patient diagnosis and treatment. The use of Conventional Neural Networks (CNN) for the classification and diagnosis of medical images using big datasets requires, in most cases, the use of special high-performance computing machines, which are very expensive and hard to access by most researchers. A new form of Machine Learning (ML), Quantum machine learning (QML), is being introduced as an emerging strategy to overcome this problem. A hybrid quantum-classical CNN uses both quantum and classical convolution layers designed to use a parameterized quantum circuit. This means that the computing model utilizes a quantum circuits approach to construct QML algorithms, which are then used to transform the quantum state to extract image hidden features. This computational acceleration is expected to achieve better algorithm performance than classical CNNs. This study intends to evaluate the performance of a Hybrid Quantum CNN (HQCNN) against a conventional CNN. This is followed by some optimizer modifications for both proposed and classical CNN methods to investigate the possible further improvement of their performance. The optimizer modification is based on forcing the optimizer to be directly adaptive to model accuracy. The optimizer adaptiveness is based on the development of an optimizer with a loss base adaptive momentum. Several algorithms are developed to achieve the above-mentioned goals, including CNN, QCNN, CNN with the adaptive optimizer, and QCNN with the Adaptive optimizer. The four algorithms are tested against a Kaggle brain dataset containing over 7000 samples. The test results show the hybrid quantum circuit algorithm outperformed the conventional CNN algorithm. The performance of both algorithms was further improved by using a fully adaptive SGD optimizer.

Optical image conversion and encryption based on structured light illumination and a diffractive neural network

In this paper, an optical image encryption method is proposed based on structured light illumination and a diffractive neural network (DNN), which can realize conversion between different images. With the use of the structured phase mask (SPM) in the iterative phase retrieval algorithm, a plaintext image is encoded into a DNN composed of multiple phase-only masks (POMs) and ciphertext. It is worth noting that ciphertext is a visible image such that the conversion of one image to another is achieved, leading to high concealment of the proposed optical image encryption method. In addition, the wavelength of the illuminating light, all Fresnel diffraction distances, the optical parameters of the adopted SPM such as focal length and topological charge number, as well as all POMs in the DNN are all considered as security keys in the decryption process, contributing to a large key space and high level of security. Numerical simulations are performed to demonstrate the feasibility of the proposed method, and simulation results show that it exhibits high feasibility and safety as well as strong robustness.

Coupling Quantum Random Walks with Long- and Short-Term Memory for High Pixel Image Encryption Schemes

This paper proposes an encryption scheme for high pixel density images. Based on the application of the quantum random walk algorithm, the long short-term memory (LSTM) can effectively solve the problem of low efficiency of the quantum random walk algorithm in generating large-scale pseudorandom matrices, and further improve the statistical properties of the pseudorandom matrices required for encryption. The LSTM is then divided into columns and fed into the LSTM in order for training. Due to the randomness of the input matrix, the LSTM cannot be trained effectively, so the output matrix is predicted to be highly random. The LSTM prediction matrix of the same size as the key matrix is generated based on the pixel density of the image to be encrypted, which can effectively complete the encryption of the image. In the statistical performance test, the proposed encryption scheme achieves an average information entropy of 7.9992, an average number of pixels changed rate (NPCR) of 99.6231%, an average uniform average change intensity (UACI) of 33.6029%, and an average correlation of 0.0032. Finally, various noise simulation tests are also conducted to verify its robustness in real-world applications where common noise and attack interference are encountered.

Agrast-6: Abridged VGG-Based Reflected Lightweight Architecture for Binary Segmentation of Depth Images Captured by Kinect

Binary object segmentation is a sub-area of semantic segmentation that could be used for a variety of applications. Semantic segmentation models could be applied to solve binary segmentation problems by introducing only two classes, but the models to solve this problem are more complex than actually required. This leads to very long training times, since there are usually tens of millions of parameters to learn in this category of convolutional neural networks (CNNs). This article introduces a novel abridged VGG-16 and SegNet-inspired reflected architecture adapted for binary segmentation tasks. The architecture has 27 times fewer parameters than SegNet but yields 86% segmentation cross-intersection accuracy and 93% binary accuracy. The proposed architecture is evaluated on a large dataset of depth images collected using the Kinect device, achieving an accuracy of 99.25% in human body shape segmentation and 87% in gender recognition tasks.

Color image encryption scheme based on alternate quantum walk and controlled Rubik's Cube

Aiming at solving the trouble that digital image information is easily intercepted and tampered during transmission, we proposed a color image encryption scheme based on alternate quantum random walk and controlled Rubik’s Cube transformation. At the first, the color image is separated into three channels: channel R, channel G and channel B. Besides, a random sequence is generated by alternate quantum walk. Then the six faces of the Rubik’s Cube are decomposed and arranged in a specific order on a two-dimensional plane, and each pixel of the image is randomly mapped to the Rubik’s Cube. The whirling of the Rubik’s Cube is controlled by a random sequence to realize image scrambling and encryption. The scrambled image acquired by Rubik’s Cube whirling and the random sequence received by alternate quantum walk are bitwise-XORed to obtain a single-channel encrypted image. Finally the three-channel image is merged to acquire the final encrypted image. The decryption procedure is the reverse procedure of the encryption procedure. The key space of this scheme is theoretically infinite. After simulation experiments, the information entropy after encryption reaches 7.999, the NPCR is 99.5978%, and the UACI is 33.4317%. The encryption scheme with high robustness and security has a excellent encryption effect which is effective to resist statistical attacks, force attacks, and other differential attacks.

Attribute-Based Encryption in Securing Big Data from Post-Quantum Perspective: A Survey

Attribute-based encryption (ABE) cryptography is widely known for its potential to solve the scalability issue of recent public key infrastructure (PKI). It provides a fine-grained access control system with high flexibility and efficiency by labeling the secret key and ciphertext with distinctive attributes. Due to its fine-grained features, the ABE scheme is a protection layer in securing users’ data and privacy in big data processing and analytics. However, quantum computing, new technology on the horizon that will transform the security and privacy environment, has begun to appear. Like the conventional ABE schemes, present cryptography is not excluded from the impacts of quantum technology as they are not made to be quantum-resistant. While most recent surveys generally touched on the generic features of attribute-based encryption schemes such as user revocation, scalability, flexibility, data confidentiality, and scope in pairing-based ABE schemes, this survey investigated quantum-resistant ABE schemes in securing big data. This survey reviews the challenges faced by the recent ABE cryptography in the post-quantum era and highlights its differences from the conventional pairing-based ABE schemes. Subsequently, we defined the criteria of an ideal quantum-resistant ABE scheme. Additionally, existing works on quantum-resistant ABE schemes are reviewed based on their algorithms design, security and functionalities. Lastly, we summarized quantum-resistant ABE schemes’ ongoing challenges and future works.