Neural Cryptography Based on Complex-Valued Neural Network

Variable Gain Impulsive Synchronization for Discrete-Time Delayed Neural Networks and Its Application in Digital Secure Communication

This article revisits the problems of impulsive stabilization and impulsive synchronization of discrete-time delayed neural networks (DDNNs) in the presence of disturbance in the input channel. A new Lyapunov approach based on double Lyapunov functionals is introduced for analyzing exponential input-to-state stability (EISS) of discrete impulsive delayed systems. In the framework of double Lyapunov functionals, a pair of timer-dependent Lyapunov functionals are constructed for impulsive DDNNs. The pair of Lyapunov functionals can introduce more degrees of freedom that not only can be exploited to reduce the conservatism of the previous methods, but also make it possible to design variable gain impulsive controllers. New design criteria for impulsive stabilization and impulsive synchronization are derived in terms of linear matrix inequalities. Numerical results show that compared with the constant gain design technique, the proposed variable gain design technique can accept larger impulse intervals and equip the impulsive controllers with a stronger disturbance attenuation ability. Applications to digital signal encryption and image encryption are provided which validate the effectiveness of the theoretical results.

Complex Relation Embedding for Scene Graph Generation

Given an input image, scene graph generation (SGG) aims to generate comprehensive visual relationships between objects in the form of graphs. Recently, more attention to the design of complex networks and complicated strategies has been paid to the long tail issue caused by the imbalanced class distribution. However, most existing methods adopt the concatenated features of two objects in real space as the final relation representation for a given triplet. We mainly argue that such a simple concatenation may neglect the importance of complex interactions between objects, which results in the diversity of visual relations. In addition, the representation learning in real space is also inadequate to express this property. To alleviate these issues, we seamlessly incorporate Hermitian inner product into existing models to facilitate the generation of scene graphs by learning Relation Embedding in Complex space (CoRE). More specifically, we first introduce the concept of complex-valued representations for entities and then formulate the relation triplets with Hermitian inner product in complex space. Finally, we investigate the effect of utilizing only real component or both of Hermitian inner product on inferring more reasonable interaction between objects for scene graphs. Comprehensive experiments on two widely used benchmark datasets, Visual Genome (VG) and Open Image, demonstrate our effectiveness, superiority, and generalization on various metrics for biased or unbiased inference.

Spectrum learning for super-resolution tomographic reconstruction

Objective. Computed Tomography (CT) has been widely used in industrial high-resolution non-destructive testing. However, it is difficult to obtain high-resolution images for large-scale objects due to their physical limitations. The objective is to develop an improved super-resolution technique that preserves small structures and details while efficiently capturing high-frequency information.Approach. The study proposes a new deep learning based method called spectrum learning (SPEAR) network for CT images super-resolution. This approach leverages both global information in the image domain and high-frequency information in the frequency domain. The SPEAR network is designed to reconstruct high-resolution images from low-resolution inputs by considering not only the main body of the images but also the small structures and other details. The symmetric property of the spectrum is exploited to reduce weight parameters in the frequency domain. Additionally, a spectrum loss is introduced to enforce the preservation of both high-frequency components and global information.Main results. The network is trained using pairs of low-resolution and high-resolution CT images, and it is fine-tuned using additional low-dose and normal-dose CT image pairs. The experimental results demonstrate that the proposed SPEAR network outperforms state-of-the-art networks in terms of image reconstruction quality. The approach successfully preserves high-frequency information and small structures, leading to better results compared to existing methods. The network's ability to generate high-resolution images from low-resolution inputs, even in cases of low-dose CT images, showcases its effectiveness in maintaining image quality.Significance. The proposed SPEAR network's ability to simultaneously capture global information and high-frequency details addresses the limitations of existing methods, resulting in more accurate and informative image reconstructions. This advancement can have substantial implications for various industries and medical diagnoses relying on accurate imaging.

The dynamics of octonion-valued neutral type high-order Hopfield neural networks with D operator

In this paper, the existence, uniqueness and global exponential stability of pseudo almost periodic solutions for a class of octonion-valued neutral type high-order Hopfield neural network models with D operator are established by using the Banach fixed point theorem and differential inequality techniques. Compared with most existing models, in this class of networks, all connection weights and activation functions are assumed to be octonion-valued functions except for time delays. And unlike most of the existing methods of studying octonion-valued neural networks, our method is a non-decomposition method, that is, the method of directly studying octonion-valued systems. The results and methods in this paper are new. In addition, an example and its numerical simulation are given to illustrate the feasibility of our results.

Pattern Formation in a Reaction-Diffusion BAM Neural Network With Time Delay: (k1, k2) Mode Hopf-Zero Bifurcation Case

This article investigates the joint effects of connection weight and time delay on pattern formation for a delayed reaction-diffusion BAM neural network (RDBAMNN) with Neumann boundary conditions by using the (k₁,k₂) mode Hopf-zero bifurcation. First, the conditions for k₁ mode zero bifurcation are obtained by choosing connection weight as the bifurcation parameter. It is found that the connection weight has a great impact on the properties of steady state. With connection weight increasing, the homogeneous steady state becomes inhomogeneous, which means that the connection weight can affect the spatial stability of steady state. Then, the specified conditions for the k₂ mode Hopf bifurcation and the (k₁,k₂) mode Hopf-zero bifurcation are established. By using the center manifold, the third-order normal form of the Hopf-zero bifurcation is obtained. Through the analysis of the normal form, the bifurcation diagrams on two parameters' planes (connection weight and time delay) are obtained, which contains six areas. Some interesting spatial patterns are found in these areas: a homogeneous periodic solution, a homogeneous steady state, two inhomogeneous steady state, and two inhomogeneous periodic solutions.

Supervised Learning in Neural Networks: Feedback-Network-Free Implementation and Biological Plausibility

The well-known backpropagation learning algorithm is probably the most popular learning algorithm in artificial neural networks. It has been widely used in various applications of deep learning. The backpropagation algorithm requires a separate feedback network to back propagate errors. This feedback network must have the same topology and connection strengths (weights) as the feed-forward network. In this article, we propose a new learning algorithm that is mathematically equivalent to the backpropagation algorithm but does not require a feedback network. The elimination of the feedback network makes the implementation of the new algorithm much simpler. The elimination of the feedback network also significantly increases biological plausibility for biological neural networks to learn using the new algorithm by means of some retrograde regulatory mechanisms that may exist in neurons. This new algorithm also eliminates the need for two-phase adaptation (feed-forward phase and feedback phase). Hence, neurons can adapt asynchronously and concurrently in a way analogous to that of biological neurons.

AI Makes Crypto Evolve

The recent literature reveals a dichotomy formed by a coevolution between cryptography and Artificial Intelligence (AI). This dichotomy consists of two sides, namely Crypto-Influenced AI (CIAI) and AI-Influenced Cryptography (AIIC). While it is pertinent to investigate this dichotomy from both sides, the first side has already been studied. In this review, we focused on AIIC. We identified and analyzed the stages on the evolutionary path of AIIC. Moreover, we attempted to anticipate what the future may hold for AIIC given the impact of quantum computing on the present and the future of AI.

Instant-Hybrid Neural-Cryptography (IHNC) based on fast machine learning

Nowadays, cryptographic systems’ designers are facing significant challenges in their designs. They have to constantly search for new ideas of fast unbreakable algorithms with a very powerful key generator. In this paper, we propose a novel hybrid neural-cryptography methodology. It depends on new rule of very fast Backpropagation (BP) instant machine learning (ML). This proposed Hybrid Cryptography system is constructed from Encryptor and Decryptor based on the asymmetric Autoencoder type. The Encryptor encrypts and compresses a set of data to be instant code (i-code) using public key. While the Decryptor recovers this i-code (ciphered-data) based on two keys together. The first is the private key and the other is called instant-key (i-key). This i-key is generated from 3 factors as well (the original data itself, the generated i-code and the private key). The i-key is changing periodically with every transformation of plain data set, so it is powerful unpredictable key against the brute force.

The Dichotomy of Neural Networks and Cryptography: War and Peace

In recent years, neural networks and cryptographic schemes have come together in war and peace; a cross-impact that forms a dichotomy deserving a comprehensive review study. Neural networks can be used against cryptosystems; they can play roles in cryptanalysis and attacks against encryption algorithms and encrypted data. This side of the dichotomy can be interpreted as a war declared by neural networks. On the other hand, neural networks and cryptographic algorithms can mutually support each other. Neural networks can help improve the performance and the security of cryptosystems, and encryption techniques can support the confidentiality of neural networks. The latter side of the dichotomy can be referred to as the peace. There are, to the best of our knowledge, no current surveys that take a comprehensive look at the many ways neural networks are currently interacting with cryptography. This survey aims to fill that niche by providing an overview on the state of the cross-impact between neural networks and cryptography systems. To this end, this paper will highlight the current areas where progress is being made as well as the aspects where there is room for future research to be conducted.

Synchronization of Tree Parity Machines Using Nonbinary Input Vectors

Neural cryptography is the application of artificial neural networks (ANNs) in the subject of cryptography. The functionality of this solution is based on a tree parity machine (TPM). It uses ANNs to perform secure key exchange between network entities. This brief proposes improvements to the synchronization of two TPMs. The improvement is based on learning ANN using input vectors that have a wider range of values than binary ones. As a result, the duration of the synchronization process is reduced. Therefore, TPMs achieve common weights in a shorter time due to the reduction of necessary bit exchanges. This approach improves the security of neural cryptography.

Chaotic Image Encryption: State-of-the-Art, Ecosystem, and Future Roadmap

Recently, many researchers have been interested in the application of chaos in cryptography. Specifically, numerous research works have been focusing on chaotic image encryption. A comprehensive survey can highlight existing trends and shed light on less-studied topics in the area of chaotic image encryption. In addition to such a survey, this paper studies the main challenges in this field, establishes an ecosystem for chaotic image encryption, and develops a future roadmap for further research in this area.

Information Fusion in Autonomous Vehicle Using Artificial Neural Group Key Synchronization

Information fusion in automated vehicle for various datatypes emanating from many resources is the foundation for making choices in intelligent transportation autonomous cars. To facilitate data sharing, a variety of communication methods have been integrated to build a diverse V2X infrastructure. However, information fusion security frameworks are currently intended for specific application instances, that are insufficient to fulfill the overall requirements of Mutual Intelligent Transportation Systems (MITS). In this work, a data fusion security infrastructure has been developed with varying degrees of trust. Furthermore, in the V2X heterogeneous networks, this paper offers an efficient and effective information fusion security mechanism for multiple sources and multiple type data sharing. An area-based PKI architecture with speed provided by a Graphic Processing Unit (GPU) is given in especially for artificial neural synchronization-based quick group key exchange. A parametric test is performed to ensure that the proposed data fusion trust solution meets the stringent delay requirements of V2X systems. The efficiency of the suggested method is tested, and the results show that it surpasses similar strategies already in use.

Chimera states and cluster solutions in Hindmarsh-Rose neural networks with state resetting process

The neuronal state resetting model is a hybrid system, which combines neuronal system with state resetting process. As the membrane potential reaches a certain threshold, the membrane potential and recovery current are reset. Through the resetting process, the neuronal system can produce abundant new firing patterns. By integrating with the state resetting process, the neuronal system can generate irregular limit cycles (limit cycles with impulsive breakpoints), resulting in repetitive spiking or bursting with firing peaks which can not exceed a presetting threshold. Although some studies have discussed the state resetting process in neurons, it has not been addressed in neural networks so far. In this paper, we consider chimera states and cluster solutions in Hindmarsh-Rose neural networks with state resetting process. The network structures are based on regular ring structures and the connections among neurons are assumed to be bidirectional. Chimera and cluster states are two types of phenomena related to synchronization. For neural networks, the chimera state is a self-organization phenomenon in which some neuronal nodes are synchronous while the others are asynchronous. Cluster synchronization divides the system into several subgroups based on their synchronization characteristics, with neuronal nodes in each subgroup being synchronous. By improving previous chimera measures, we detect the spike inspire time instead of the state variable and calculate the time between two adjacent spikes. We then discuss the incoherence, chimera state, and coherence of the constructed neural networks using phase diagrams, time series diagrams, and probability density histograms. Besides, we further contrast the cluster solutions of the system under local and global coupling, respectively. The subordinate state resetting process enriches the firing mode of the proposed Hindmarsh-Rose neural networks.

Chaos coordinated neural key synchronization for enhancing security of IoT

The key exchange mechanism in this paper is built utilizing neural network coordination and a hyperchaotic (or chaotic) nonlinear dynamic complex system. This approach is used to send and receive sensitive data between Internet-of-Things (IoT) nodes across a public network. Using phishing, Man-In-The-Middle (MITM), or spoofing attacks, an attacker can easily target sensitive information during the exchange process. Furthermore, minimal research has been made on the exchange of input seed values for creating identical input at both ends of neural networks. The proposed method uses a 5D hyperchaotic or chaotic nonlinear complex structure to ensure the sharing of input seed value across two neural networks, resulting in the identical input on both ends. This study discusses two ways for sharing seed values for neural coordination. The first is a chaotic system with all real variables, whereas the second is a hyperchaotic system with at least one complex variable. Each neural network has its own random weight vector, and the outputs are exchanged. It achieves full coordination in some stages by altering the neuronal weights according to the mutual learning law. The coordinated weights are utilized as a key after the neural coordination technique. The network’s core structure is made up of triple concealed layers. So, determining the inner configuration will be tough for the intruder. The efficiency of the suggested model is validated by simulations, and the findings reveal that the suggested strategy outperforms current equivalent techniques.

Chaos-guided neural key coordination for improving security of critical energy infrastructures

In this paper, chaos-guided artificial neural learning-based session key coordination for industrial internet-of-things (IIoT) to enhance the security of critical energy infrastructures (CEI) is proposed. An intruder might pose several security problems since the data are transferred across a public network. Although there have been substantial efforts to solve security problems in the IIoT, the majority of them have relied on traditional methods. A wide range of privacy issues (secrecy, authenticity, and access control) must be addressed to protect IIoT systems against attack. Owing to the unique characteristics of IIoT nodes, existing solutions do not properly address the entire security range of IIoT networks. To deal with this, a chaos-based triple layer vector-valued neural network (TLVVNN) is proposed in this paper. A chaos-based exchange of common seed value for the generation of the identical input vector at both transmitter and receiver is also proposed. This technique has several advantages, including (1) it protects IIoT devices by utilizing TLVVNN synchronization to improve CEI security. (2) Here, artificial neural coordination is utilized for the exchange of neural keys between two IIoT nodes. (3) Using this suggested methodology, chaotic synchronization can be achieved, enabling the chaos-based PRNG seed exchange. (4) Vector-valued inputs and weights are taken into consideration for TLVVNN networks. (5) The deep internal architecture is made up of three hidden layers of the neural network and a vector value as input. As a result, the attacker would have great difficulty interpreting the internal structure. Experiments to verify the performance of the proposed technique are conducted, and the findings demonstrate that the proposed technique has greater performance benefits than the existing related techniques.

Mutual learning-based efficient synchronization of neural networks to exchange the neural key

Synchronization of two neural networks through mutual learning is used to exchange the key over a public channel. In the absence of a weight vector from another party, the key challenge with neural synchronization is how to assess the coordination of two communication parties. There is an issue of delay in the current techniques in the synchronization assessment that has an impact on the security and privacy of the neural synchronization. In this paper, to assess the complete coordination of a cluster of neural networks more efficiently and timely, an important strategy for assessing coordination is presented. To approximately determine the degree of synchronization, the frequency of the two networks having the same output in prior iterations is used. The hash is used to determine if both the networks are completely synchronized exactly when a certain threshold is crossed. The improved technique makes absolute coordination between two communication parties using the weight vectors’ has value. In contrast, with existing approaches, two communicating parties who follow the proposed approach will detect complete synchronization sooner. This reduces the effective geometric likelihood. The proposed method, therefore, increases the safety of the protocol for neural key exchange. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

Neural synchronization is a technique for establishing the cryptographic key exchange protocol over a public channel. Two neural networks receive common inputs and exchange their outputs. In some steps, it leads to full synchronization by setting the discrete weights according to the specific rule of learning. This synchronized weight is used as a common secret session key. But there are seldom research is done to investigate the synchronization of a cluster of neural networks. In this paper, a Generative Adversarial Network (GAN)-based synchronization of a cluster of neural networks with three hidden layers is proposed for the development of the public-key exchange protocol. This paper highlights a variety of interesting improvements to traditional GAN architecture. Here GAN is used for Pseudo-Random Number Generators (PRNG) for neural synchronization. Each neural network is considered as a node of a binary tree framework. When both i-th and j-th nodes of the binary tree are synchronized then one of these two nodes is elected as a leader. Now, this leader node will synchronize with the leader of the other branch. After completion of this process synchronized weight becomes the session key for the whole cluster. This proposed technique has several advantages like (1) There is no need to synchronize one neural network to every other in the cluster instead of that entire cluster can be able to share the same secret key by synchronizing between the elected leader nodes with only logarithmic synchronization steps. (2) This proposed technology provides GAN-based PRNG which is very sensitive to the initial seed value. (3) Three hidden layers leads to the complex internal architecture of the Tree Parity Machine (TPM). So, it will be difficult for the attacker to guess the internal architecture. (4) An increase in the weight range of the neural network increases the complexity of a successful attack exponentially but the effort to build the neural key decreases over the polynomial time. (5) The proposed technique also offers synchronization and authentication steps in parallel. It is difficult for the attacker to distinguish between synchronization and authentication steps. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.