ABSTRACT Freshness is a core quality indicator that determines the utilisation and commercial value of fish products. Traditional fish freshness detection methods are highly subjective and destructive, while existing neural network models suffer from low detection accuracy, unsatisfactory recall and confidence scores and limited generalisation ability. To address these limitations, this paper proposes a novel Dual‐Sensitive Convolutional Neural Network (S‐CNN), where the letter ‘S’ stands for Sensitive. The model simultaneously extracts and fuses discriminative features from fish eye and gill images, capturing subtle freshness differences through a dual‐sensitive feature extraction mechanism. In data preprocessing, all image pixels are normalised to the range [0, 1] to unify numerical scales, stabilise gradient descent and mitigate overfitting. The proposed S‐CNN is composed of seven convolutional blocks, each equipped with batch normalisation, L2 regularisation and a pooling layer; the pooling operation is omitted in the last block to avoid excessive dimensionality reduction. After the flatten layer, a Dropout regularisation module is adopted, and L2 regularisation is applied to all convolutional and fully connected layers. The network uses categorical crossentropy as the loss function. Experimental results demonstrate that the S‐CNN achieves a detection accuracy of 98.70% and an average confidence score of 99.18% on the fish freshness dataset, outperforming other comparative models. The results confirm that the fusion of fish eye and gill features can effectively evaluate fish freshness, providing a reliable method for nondestructive detection and quality assessment of fish products.

With the popularity of cloud storage, video data, especially videos containing personal information, faces serious security challenges. However, existing video encryption schemes typically adopt full-frame encryption, resulting in high computational overhead, low efficiency, and difficulty balancing privacy protection and lightweight encryption requirements. To this end, a lightweight video encryption scheme based on object detection and adaptive frame multiplexing is designed in this paper. First, the YOLOv8 algorithm is employed to accurately identify multiple human target regions in videos, thereby avoiding the computational resource waste associated with full-frame encryption. Second, combined with SCI-HMC hyperchaotic map, an adaptive frame multiplexing strategy is adopted to realize the dynamic adjustment of chaotic sequences by correlating the encryption process before and after. On this basis, a cube lightweight encryption algorithm based on video frame combination is designed, which is spliced layer by layer in terms of color channels, traversed in terms of 3 layers of data (one video frame), and performs the 3D confusion and 3D mod diffusion sequentially according to the target coordinates, and finally realizes the accurate encryption of the region of interest. The experimental results show that the scheme performs well in terms of practicality and resistance to attacks. The information entropy of the encrypted area is as high as 7.9982, and the encryption speed can be increased to 0.2343 seconds per frame. This deep collaboration framework tightly integrates modern object detection with dynamic encryption processes, providing a balanced security and lightweight solution for cloud video data protection.

To address the high computational costs of full-frame encryption and the risk of exposing sensitive locations in partial encryption, this paper proposes a video selective encryption and steganography scheme based on object detection and image inpainting. First, YOLOv8 is employed to achieve real-time and accurate detection of human targets in video frames. Then, the LIS-HMC hyperchaotic map and a new chaotic-driven interframe chain modulation (CDICM) strategy, combined with a designed row-column interchange and Roller confusion algorithm, are applied to selectively encrypt the target regions. Next, the globally and locally consistent image completion (GLCIC) algorithm is used to restore the background panoramically, eliminating visual discontinuities. Meanwhile, based on the Walsh-Hadamard transform (WHT), a multi-round embedding (MRE) steganography strategy is developed to hide the encrypted information within the restored background. Experimental results show that the encrypted data achieve an information entropy of 7.9925, a steganographic capacity of 0.75 bpp, and a PSNR above 44.91 dB after data embedding, demonstrating that the proposed method provides a new solution for video privacy protection that balances security, real-time performance, and visual naturalness.

With the rapid development of the electronic information industry, massive private data are continuously uploaded to the Internet, posing severe challenges to data security. Thus, a high-capacity private data information protection library based on correlation generator is proposed. For private data uploaded by multiple individuals or organizations, the proposed library enables efficient bulk protection. Through the biometric images held by individuals or organizations, correlation values are generated by the correlation generator, which are combined with such initial values of the four dimensional hyperchaotic system (4DHS) to generate private keys and master keys. The chaotic sequences generated by the iteration of the system are combined with the encryption scheme to provide effective protection of private data information. Afterwards, the scheme is tested for simulation and security, which verify the feasibility and security of the proposed scheme.

In biological decision-making, adaptive behavior arises from the interaction between structured task context, expectation, action selection, and feedback-based learning. While most existing studies reproduce reward-driven responses under clear sensory stimuli, decision formation under weak or absent sensory evidence, such as low or 0% contrast conditions, remains insufficiently explored. To address this issue, this work proposes a biologically plausible memristive decision-making framework based on a block-structured task paradigm. The proposed system adopts a closed-loop architecture composed of four functional modules: stimulus, expectation, action, and reward/punishment. Sensory information is encoded when available, while the expectation pathway provides prior-guided modulation when sensory evidence becomes weak or unreliable. Action selection is generated through competitive integration, and reward–punishment feedback dynamically corrects decision bias and reinforces appropriate responses. Through this hierarchical interaction, stable decision behavior can be achieved even in the absence of explicit sensory inputs. PSPICE simulations are conducted to analyze system dynamics and validate the corrective role of the reward–punishment mechanism under weak and ambiguous conditions. In addition, the proposed framework is demonstrated in an industrial autonomous navigation scenario, illustrating its scalability and applicability for adaptive decision-making under uncertainty.

In recent years, chaos-based multimedia cryptosystems have gained prominence due to their nonlinear properties, such as sensitivity to initial conditions and long-term unpredictability, which parallel the cryptographic requirements of confusion and diffusion. However, many such systems lack standardization and deviate from secure design principles, resulting in practical vulnerabilities. This article presents a comprehensive cryptanalysis of a widely cited video cryptosystem. The target system combines S-box substitution—derived from either a 12D chaotic map or the Ikeda delay differential equation (DDE)—with a Cipher Block Chaining (CBC) diffusion scheme. Through an analysis of the encryption structure, fundamental design defects are identified. Specifically, the CBC diffusion mechanism lacks key dependence, and the system exhibits an excessive reliance on fixed, publicly exposed S-boxes. These vulnerabilities are demonstrated through chosen-plaintext attacks, known-plaintext attacks, and chosen-ciphertext attacks. Experimental results confirm that the S-box can be fully reconstructed, thereby facilitating the complete decryption of video content in the absence of the secret key. Beyond exposing vulnerabilities, this study offers constructive contributions by proposing six concrete improvement strategies, including dynamic key generation, structural enhancement, and dynamic S-box indexing. This work provides practical suggestions for designing secure chaos-based multimedia cryptosystems, offering valuable references for future research and promoting the development of efficient encryption systems.

In the digital age, surveillance videos face severe security threats during transmission. Chaotic systems are often used for encrypted transmission due to their sensitivity to initial conditions and unpredictability. However, existing chaotic encryption schemes are at risk of core information leakage, lack adaptive detection of targets, and are inefficient. To address these issues, this article proposes a lightweight video secondary-encryption scheme integrating YOLOv11 and a Discrete Bi-Neuron Hopfield Neural Network (DBHNN). The YOLOv11 model is used to detect sensitive objects in the video, enabling the scheme to further protect sensitive information. The hyperchaotic sequences generated by DBHNN are used for lightweight secondary-encryption: the point-to-point confusion for target detection objects. Subsequently, enhanced alternating confusion and diffusion are applied to encrypt all frames. The proposed scheme can process batch frames and perform secondary encryption on sensitive objects to enhance security. The simulations and tests show that the proposed lightweight encryption scheme has an encryption speed that is more than 5% better than other schemes, and YOLOv11 is also superior to other models in terms of accuracy and efficiency.

To solve the problem of resource consumption and information security during color image transmission, multiple color images encryption scheme according to a three-dimensional discrete chaotic map with pseudo-random number signal generator and discrete wavelet transform (DWT) compression is proposed. Firstly, dynamics of three-dimensional discrete chaotic map is analyzed and found to provide better randomness for encryption schemes. Next, multiple color images of different sizes are compressed to 1/4 of the original size after DWT processing. The multiple compressed images are merged into a plaintext cube, and the plaintext parameters associated with the cube are generated. The generated plaintext parameters are combined with the chaotic map to form the key. A series of sequences are generated by iteration for image confusion and diffusion to get cipher images. The final simulation results show that recovered plaintext image is still clearly visible even with lossy DWT compression. The security analysis results indicate that this scheme has high level of security protection for color images.

Images are widely used in social networks, necessitating efficient and secure transmission, especially in bandwidth-constrained environments. This article aims to develop a color image encryption algorithm that enhances security while optimizing computational efficiency. A novel parallel color image encryption algorithm based on the 2-D logistic-Rulkov neuron map (2D-LRNM) is proposed. In this approach, the three channels of the color image are first separated. Cross-channel information interaction is introduced to form three new channels, which are then processed in parallel. During the encryption process of each channel, a block-wise parallel encryption mechanism is applied, ensuring simultaneous encryption of each block. This block-wise strategy effectively leverages parallel computing resources and balances the task load. To meet the demand for a large number of keystreams during encryption, the 2D-LRNM is introduced. It combines the simplicity and chaotic properties of the Logistic map with the multitimescale dynamics and neurodynamic behaviors of the Rulkov map. By overcoming the dimensional limitations inherent in the single Logistic map, this approach extends the system to a 2-D framework, significantly increasing the complexity of chaotic behavior and improving its unpredictability. Experimental results demonstrate that the proposed encryption algorithm achieves high security and reduces computation time by approximately 83.3%.

Considering the extremely complex physiological environment within neurons, there is feedback from autapse currents as well as the influence of external electromagnetic radiation. In this paper, a second-order memristor is constructed based on the definition of a generic memristor, which two intermediate variables are used to simultaneously model the effects of electromagnetic radiation and autapse on Rulkov neuron, called SOM-Rulkov neuron. The analysis of Lyapunov Exponent spectrum(LEs), bifurcation diagrams, phase diagrams, and iterative diagrams with different parameters that SOM-Rulkov has various types of periodic and chaotic firing patterns and high complexity. In particular, homogeneous extreme multistability is demonstrated with different initial conditions, and the phenomenon is more suitable for image encryption. Furthermore, the SOM-Rulkov map is implemented on the DSP platform. Finally, the SOM-Rulkov map is applied to encrypt the 3D model, which is essentially a sequence generated by homogeneous multistability and the vertex coordinates of the 3D model for different position xor operations. When decrypting, users with different levels of keys can access different visualizations. Experiments show that the scheme has strong security and low time cost.

Discrete chaotic systems based on memristors exhibit excellent dynamical properties and are more straightforward to implement in hardware, making them highly suitable for generating cryptographic keystreams. However, most existing memristor-based chaotic systems rely on a single memristor. This paper introduces a novel discrete chaotic system employing dual memristors, named the 3D memristive cubic map with dual discrete memristors (3D-MCM). The 3D-MCM system demonstrates richer and more intricate dynamical behaviors compared to its single-memristor counterparts, as verified through bifurcation diagrams, Lyapunov exponent spectra, and complexity analyses. Notably, the system exhibits coexisting attractors, substantially enhancing its dynamical complexity. Hardware implementation of the 3D-MCM attractors confirms its feasibility for industrial applications. To illustrate the system’s potential in encryption tasks, this study integrates the quaternary-based permutation and dynamic emanating diffusion (QPDED-IE) scheme with the 3D-MCM for image encryption. Experimental results demonstrate that the QPDED-IE scheme based on the 3D-MCM exhibits strong diffusion and confusion properties, effectively resisting cryptanalytic attacks.

Traditional video encryption methods protect video content by encrypting each frame individually. However, in resource-constrained environments, this approach consumes significant computational resources. To overcome this challenge, this paper proposes a novel method called “Encrypt a story (EAS)”, which aims to enhance encryption efficiency by focusing on encrypting specific segments of the video rather than encrypting each frame. The EAS refers to selecting segments in the time dimension of the video that contain important information or key events for encryption. This method leverages video segmentation techniques to focus encryption efforts on continuous key frames, significantly reducing the consumption of computational resources. To address the need for a large number of key streams during the encryption process, this paper proposes a discrete sinusoidal memristive Rulkov neuron map (DSM-RNM). Through attractor analysis, complexity comparison, Lyapunov exponent, and NIST tests, we validated its ability to generate high-performance pseudorandom sequences, which significantly enhances the security of the encryption algorithm. Notably, the DSM-RNM is shown to exhibit a phenomenon of infinitely coexisting attractors. Furthermore, by constructing a digital circuit to capture the attractors of the DSM-RNM, its potential for industrial applications is demonstrated. Evaluation results show that the EAS saves approximately 90% of the time while ensuring security, exhibiting strong practicality and efficiency

The security of a chaos-based image encryption (IE) systems is based upon chaotic map’s performance and the encryption algorithm’s permutation and diffusion strategies. Nevertheless, existing IE schemes exhibit different drawbacks, such as limited disordering capabilities, inadequate dynamic performance, and the chaotic maps’ insensitivity. To address these limitations, this study presents an octal-based shuffling and multilayer rotational diffusing IE (OSMRD-IE) utilizing a 2-D hybrid Michalewicz–Ackley (2-D-HMA) map. The 2-D-HMA map has the capability to generate new hyperchaotic maps by integrating hybrid functions using different encapsulation functions. The integration of a map generator could lead to dynamic nature, chaotic perturbations, and parameter control mechanisms. To enhance the algorithm’s resilience against cyberthreats, the 2-D-HMA map-based OSMRD-IE scheme shuffles the pixels using octal-base scrambling and manipulates pixel values through multilayer rotation. By means of comparisons with existing techniques, the OSMRD-IE scheme’s reliability and 2-D-HMA map’s dynamic performance are validated independently. The superior chaotic properties of the 2-D-HMA map are evident in the experimental results, establishing OSMRD-IE as the more reliable scheme in both visual and quantitative comparisons.

Currently, discrete memristors are a focal point in the study of chaotic maps. Similar to memristors, memcapacitors-another type of memory circuit component-have not received widespread attention in the design of chaotic maps. In this article, we propose a 4-D memcapacitive hyperchaotic logistic map (4D-MHLM) by integrating memcapacitors with the logistic map. The dynamical behavior of the 4D-MHLM is analyzed using Lyapunov exponent analysis, and the impact of different parameters on system performance is discussed. The complexity of generating pseudo-random sequences with the 4D-MHLM is investigated through complexity analysis, including spectral entropy complexity and C0 complexity. Notably, attractor analysis reveals a unique phenomenon of infinite coexisting attractors within the 4D-MHLM. Finally, the chaotic attractor generated by the 4D-MHLM is successfully implemented on a hardware platform. Theoretical analysis and digital circuit implementation results indicate that the 4D-MHLM exhibits rich dynamical behavior and higher complexity, offering significant value for practical applications.

Chaos systems find extensive applications in cryptography and pseudorandom number generation due to their ability to generate pseudo-random signals. This paper focuses on enhancing the complexity of chaotic systems by introducing the memristor, a nonlinear component. We propose a novel map called the 2D memristive Cubic map (2D-MCM), which integrates the memristor with the Cubic map to create a discrete mapping. The 2D-MCM exhibits rich dynamical behavior and a broad parameter space. Notably, the 2D-MCM displays boosting bifurcation behavior. As the control parameters increase, the 2D-MCM demonstrates an expanded range of values, indicating its ability to generate a larger number of pseudo-random sequences. To validate its performance, we establish a hardware platform to physically capture the attractors of the 2D-MCM. To verify the performance of the 2D-MCM in generating pseudorandom sequences, we designed a video encryption algorithm based on the 2D-MCM. This algorithm selectively encrypts specific areas within the video, with correlation coefficients of the encrypted video in the horizontal, vertical, and diagonal directions being 0.0002, -0.0005, and 0.0004, respectively. Through simulation experiments and security analysis, we demonstrate that the 2D-MCM performs well in video encryption tasks.

To provide robust security measures for audio data during transmission, this article has developed a novel dual-channel audio encryption scheme based on chaos theory. Specifically, a new 2-D chaotic system called 2-D infinite collapse with logistic map (2-D-ICLM) is designed in this article. Compared to traditional 2-D chaotic systems, the 2-D-ICLM exhibits a larger parameter space, complexity, and richness, along with high unpredictability and randomness. These characteristics provide potential advantages and applications in the field of encryption. In the proposed encryption scheme, audio information serves as input to a hash function, which generates the initial values and parameters for the 2-D-ICLM, producing the keystream for the cryptographic system. Considering the correlation between the two channels of audio information, the information from the left and right channels is fused to create a new audio signal for encryption. Scrambling and diffusion processes are performed synchronously in the encryption algorithm, with the ciphertext information from the left channel utilized in the encryption of the right channel audio. The experimental results prove the effectiveness of the suggested audio encryption technique, effectively countering various conventional attack methods and showcasing its robust security features. The correlation of adjacent elements of ciphertext audio is 0.0013, the NSCR and UACI is around 0.9960 and 0.3345, and the efficiency is 0.0003 s/KB.

An asynchronous updating Boolean network is employed to simulate and analyze the gene expression of a particular tissue or species, revealing the life activity process from a system perspective to reveal the disease mechanism and treat the disease. Therefore, to ensure the safe transmission of the asynchronous updating Boolean network in the network, we designed an asynchronous updating Boolean network encryption algorithm based on chaos (ABNEA). First, a novel 2D chaotic system (2D-FPSM) is designed. This system has better performance than the classical 2D chaotic system. It is very suitable for cryptographic systems to generate key streams. Second, an encoding rule is designed to convert the asynchronous updating Boolean network to a Boolean matrix and propagate it on the network as an image. The receiver and sender jointly save the encoding rule. Last, to protect the safe propagation of the Boolean network matrix on the network, the method of synchronous scrambling-diffusion is adapted to encrypt the Boolean network matrix based on the 2D-FPSM. Simulation experiments and security analysis show that the average correlation of adjacent pixels of ciphertext are 0.0010, -0.0010, -0.0020, and the average information entropy is 7.9984. The ABNEA can complete the encryption tasks of asynchronously updating Boolean networks and exhibits good security characteristics.

While existing watermarking attack methods can disturb the correct extraction of watermark information, the visual quality of watermarked images will be greatly damaged. Therefore, a concealed attack based on generative adversarial network and perceptual losses for robust watermarking is proposed. First, the watermarked image is utilized as the input of generative networks, and its generating target (i.e. attacked watermarked image) is the original image. Inspired by the U-Net network, the generative networks consist of encoder-decoder architecture with skip connection, which can combine the low-level and high-level information to ensure the imperceptibility of the generated image. Next, to further improve the imperceptibility of the generated image, instead of the loss function based on MSE, a perceptual loss based on feature extraction is introduced. In addition, a discriminative network is also introduced to make the appearance and distribution of generated image similar to those of the original image. The addition of the discriminative network can remove watermark information effectively. Extensive experiments are conducted to verify the feasibility of the proposed concealed attack method. Experimental and analysis results demonstrate that the proposed concealed attack method has better imperceptibility and attack ability in comparison to the existing watermarking attack methods.