Due to their small size, low power consumption, and non-volatility, memristors are promising candidates for weight storage in ternary neural networks (TNNs). However, the inherent limitations of memristor manufacturing processes often result in faults, with stuck-at faults (SAFs) being the most prevalent, which severely degrade the accuracy and overall performance of memristor-based TNNs in practical applications. To address this challenge, a novel fault-tolerant framework is proposed to mitigate the negative impacts of SAFs. First, we analyze the factors that contribute to programmed error rates in memristor-based TNNs. The framework incorporates transformations such as flipping, permutation, and integrating redundant rows, which significantly mitigate the negative impact of SAFs and improve network accuracy. Experimental results show that even with SAF rates as high as 50% in memristor crossbar arrays, the proposed framework can effectively improve the accuracy of TNNs to near-ideal levels.

Joint encryption and compression provide an effective solution for securing image data, which is crucial for transmission and storage on cloud services such as Facebook and Twitter. Recent advancements in block-wise encryption then-compression (ETC) schemes, particularly those compatible with JPEG, strike a balance between high security and efficient compression in the application scenarios. This paper analyzes the interactions within ETC schemes applied to single-color 8×8 blocks under various attack scenarios, including ciphertext only, known-plaintext, and chosen-plaintext attacks. Then, the analysis object is further extended to conventional ETC schemes involving multiple color channels and blocks of different sizes. Notably, we introduce an advanced jigsaw puzzle solver designed to reconstruct the relative positions of sufficient blocks in the original plain-image from multiple cipher-images encrypted with the same secret key. The effectiveness of this solver is demonstrated through tests conducted on popular social media platforms such as Facebook and Weibo, underscoring its potential for real-world applications.

Over the past few decades, Internet video streaming has seen explosive growth, pushing network resources to their limits. Video Super-Resolution (VSR) technology, which enhances video quality while reducing bandwidth usage, offers a promising solution to replace traditional video delivery frameworks. However, existing real-world VSR approaches often struggle when faced with inevitable packet loss during network transmission, especially in bandwidth-constrained and low-latency environments. This packet loss introduces amplified noise and artifacts, significantly degrading visual quality. In this work, we decouple the various degrees of degradation caused by packet loss and comprehensively analyze the impact of different types of packet loss. To address these challenges, we propose ReinVSR, an efficient countermeasure strategy that mitigates the detrimental effects of packet loss without introducing additional network overhead. ReinVSR employs a two-pronged approach: a pre-restore module to mitigate missing pixel information and a Local Hidden State Attention module to rectify semantic distortions at the feature level by replacing corrupted hidden states with more accurate representations. Specifically, we leverage neighboring frames to generate a pool of hidden features, which are then refined using a novel spatial attention mechanism to aggregate more authentic and accurate hidden states. Extensive experiments demonstrate that ReinVSR outperforms state-of-the-art methods, achieving significant improvements in visual quality. It offers a robust and effective solution for high-quality video streaming in bandwidth-limited environments.

In recent years, significant developments have been made in both video retrieval and video moment retrieval tasks, which respectively retrieve complete videos or moments for a given text query. These advancements have greatly improved user satisfaction during the search process. However, previous work has failed to establish meaningful ''interaction'' between the retrieval system and the user, and its one-way retrieval paradigm can no longer fully meet the personalization and dynamic needs of at least 80.8% of users. In this paper, we introduce the Interactive Video Corpus Retrieval (IVCR) task, a more realistic setting that enables multi-turn, conversational, and realistic interactions between the user and the retrieval system. To facilitate research on this challenging task, we introduce IVCR-200K, a high-quality, bilingual, multi-turn, conversational, and abstract semantic dataset that supports video retrieval and even moment retrieval. Furthermore, we propose a comprehensive framework based on multi-modal large language models (MLLMs) to help users interact in several modes with more explainable solutions. The extensive experiments demonstrate the effectiveness of our dataset and framework. The datasets, codes, and leaderboards are available at: https://ivcr200k.github.io/IVCR.

Anomaly detection in an industrial setting is crucial for operational monitoring, yet it remains challenging under incomplete data conditions. Common issues, such as sensor failures, data transmission loss, and storage malfunctions, often result in missing data, complicating the detection of anomalies, particularly when these are localized within specific regions. To address the challenges, this paper proposes DiffANT, an unsupervised anomaly detection method that integrates a diffusion model with the Adjacent Neighborhood Transformer (ANT). Specifically, DiffANT begins by applying various data masking techniques to simulate realistic missing values that reflect real-world industrial scenarios. The ANT utilizes a Transformer encoder architecture augmented with an adjacent neighborhood attention mechanism. It effectively focuses on relevant non-immediate vicinities to enhance anomaly detection. DiffANT then reconstructs the original data from randomly sampled noise through diffusion and denoising processes and utilizes a multi-level reconstruction strategy to refine the generated samples. We demonstrate the efficacy of DiffANT through extensive experiments in diverse industrial applications, such as secure water treatment and server machine monitoring. The results indicate that DiffANT consistently outperforms state-of-the-art methods in detecting anomalies in time series data, regardless of whether the data is incomplete.

The complex dynamics of the baker's map and its variants in infinite-precision mathematical domains and quantum settings have been extensively studied over the past five decades. However, their behavior in finite-precision digital computing remains largely unknown. This paper addresses this gap by investigating the graph structure of the generalized two-dimensional baker's map and its higher-dimensional extension, referred to as HDBM, as implemented on the discrete setting in a digital computer. We provide a rigorous analysis of how the map parameters shape the in-degree bounds and distribution within the functional graph, revealing fractal-like structures intensify as parameters approach each other and arithmetic precision increases. Furthermore, we demonstrate that recursive tree structures can characterize the functional graph structure of HDBM in a fixed-point arithmetic domain. Similar to the 2-D case, the degree of any non-leaf node in the functional graph, when implemented in the floating-point arithmetic domain, is determined solely by its last component. We also reveal the relationship between the functional graphs of HDBM across the two arithmetic domains. These findings lay the groundwork for dynamic analysis, effective control, and broader application of the baker's map and its variants in diverse domains.

Understanding the underlying graph structure of a nonlinear map over a particular domain is essential in evaluating its potential for real applications. In this paper, we investigate the structure of the associated functional graph of Chebyshev permutation polynomials over a ring$\mathbb {Z}_{p^{k}}$, with p being a prime number greater than three, where every number in the ring is considered as a vertex and the existing mapping relation between two vertices is regarded as a directed edge. Based on some new properties of Chebyshev polynomials and their derivatives, we disclose how the basic structure of the functional graph evolves with respect to parameter k. First, we present a complete and explicit form of the length of a path starting from any given vertex. Then, we show that the functional graph’s strong patterns indicate that the number of cycles of any given length always remains constant as k increases. Moreover, we rigorously prove the rules on the elegant structure of the functional graph and verify them experimentally. Our results could be useful for studying the emergence mechanism of the complexity of a nonlinear map in digital computers and security analysis of its cryptographic applications.

Genomic variation is critical for understanding the genetic basis of disease. Pindel, a widely used structural variant caller, leverages short-read sequencing data to detect variation at single-base resolution; however, its hotspot module imposes substantial computational demands, limiting efficiency in large-scale whole-genome analyses. Heterogeneous architectures offer a promising solution, yet disparities in hardware design and programming models preclude direct porting of the original algorithm. To address this, we introduce MTPindel, a novel heterogeneous parallel optimization framework tailored to the MT-3000 processor. Focusing on Pindel's most compute-intensive modules, we design multi-core and task-level parallel algorithms that exploit the MT-3000's accelerator domains to balance and accelerate workload distribution. On 128 MT-3000–equipped nodes of the Tianhe next-generation supercomputer, MTPindel achieves an impressive 122.549 times of speedup and 95.74% parallel efficiency, with only a 0.74% error margin relative to the original implementation. This work represents a pioneering effort in heterogeneous parallelization for variant detection, paving the way for rapid, large-scale genomic analyses in research and clinical settings.

In the past five decades, the dynamics of Baker's map in an infinite precision world have been extensively explored. However, the real structure of Baker's map when implemented in a fixed-point arithmetic domain remains unknown. This paper gives an explicit formulation for the quantized Baker's map. We then demonstrate that the maximum in-degree of the functional graph of Baker's map is invariant under any level of fixed-point arithmetic precision. Intriguingly, we observe a self-similarity phenomenon in the functional graph of a specific Baker's map with incremental increases in precision. These findings demonstrate the consistency of Baker's map across varying precision levels. This can be utilized to streamline the dynamic analysis and application design of Baker's map and its variants in finite precision environments.

Recovering unknown, missing, damaged, distorted, or lost information in DCT coefficients is a common task in multiple applications of digital image processing, including image compression, selective image encryption, and image communication. This paper investigates the recovery of sign bits in DCT coefficients of digital images, by proposing two different approximation methods to solve a mixed integer linear programming (MILP) problem, which is NP-hard in general. One method is a relaxation of the MILP problem to a linear programming (LP) problem, and the other splits the original MILP problem into some smaller MILP problems and an LP problem. We considered how the proposed methods can be applied to JPEG-encoded images and conducted extensive experiments to validate their performances. The experimental results showed that the proposed methods outperformed other existing methods by a substantial margin, both according to objective quality metrics and our subjective evaluation.

As a paradigmatic model for nonlinear dynamics studies, the Hopfield Neural Network (HNN) demonstrates a high susceptibility to external disturbances owing to its intricate structure. This paper delves into the challenge of modulating HNN dynamics through time-variant stimuli. The effects of adjustments using two distinct types of time-variant stimuli, namely the Weight Matrix Stimulus (WMS) and the State Variable Stimulus (SVS), along with a Constant Stimulus (CS) are reported. The findings reveal that deploying four WMSs enables the HNN to generate either a four-scroll or a coexisting two-scroll attractor. When combined with one SVS, four WMSs can lead to the formation of an eight-scroll or four-scroll attractor, while the integration of four WMSs and multiple SVSs can induce grid-multi-scroll attractors. Moreover, the introduction of a CS and an SVS can significantly disrupt the dynamic behavior of the HNN. Consequently, suitable adjustment methods are crucial for enhancing the network’s dynamics, whereas inappropriate applications can lead to the loss of its chaotic characteristics. To empirically validate these enhancement effects, the study employs an FPGA hardware platform. Subsequently, an image encryption scheme is designed to demonstrate the practical application benefits of the dynamically adjusted HNN in secure multimedia communication. This exploration into the dynamic modulation of HNN via time-variant stimuli offers insightful contributions to the advancement of secure communication technologies.

Traditional fine-grained image classification relies extensively on large-scale training samples with annotated ground truth. However, in the real world, some fine-grained categories are represented by only a few available images, and existing few-shot models struggle to distinguish the subtle differences among them. Furthermore, the challenge is compounded by the fact that intra-class distances for some fine-grained categories can be significantly large, whereas inter-class distances might be minimal, leading to distinct task-specific distinguishing features for each category. To address these challenges, we propose a novel network, FicNet, utilizing Multi-Frequency Neighborhood (MFN) and Double-Cross Modulation (DCM). MFN captures a multi-frequency structure representation that is independent of the background by integrating spatial and frequency domain information, reducing intra-class distances. Concurrently, DCM modulates the representation through global context and inter-class relationships, enabling both support and query features to align with complete targets and respond to identical parts. This approach facilitates the accurate identification of subtle inter-class differences. Comprehensive experiments conducted on three fine-grained benchmark datasets for two few-shot tasks have verified that FicNet exhibits exceptional performance compared to state-of-the-art methods. Notably, it achieves classification accuracies of 93.17% and 95.36% on the “Caltech-UCSD Birds” and “Stanford Cars” datasets, respectively, surpassing the benchmarks set by general fine-grained image classification methods.

A number of image compressive sensing (CS) algorithms were proposed in the past two decades, aiming at yielding recovered images with the best possible visual effect. However, it is quite difficult to further improve the image quality for human eyes. For example, in the low-rate sampling scenarios, CS algorithms always suffer degraded performance and can only recover less visually appealing images. We notice that what human beings concern with is the visual quality of an image, while machine users care much more about its latent metrics, such as recognition accuracy, rather than the subjective visual effect. Inspired by this point, we develop a machine recognition-oriented image CS with an adversarial learning strategy. Some adversarial models are investigated to make the recognition accuracy as an additional optimization goal of the CS reconstruction network. Through end-to-end training, CS reconstruction network automatically learns an image recognition pattern, and produce recovered images owning extra recognition metric, which makes them become more suited for machine users. Experimental results indicate that the images recovered with the proposed adversarial learning strategy can be recognized with significantly higher accuracy compared to that with the existing CS algorithms.

Chaotic dynamics is an important source for generating pseudorandom binary sequences (PRBS). Much efforts have been devoted to obtaining period distribution of the generalized discrete Arnold's Cat map in various domains using all kinds of theoretical methods, including Hensel's lifting approach. Diagonalizing the transform matrix of the map, this article gives the explicit formulation of any iteration of the generalized Cat map. Then, its real graph (cycle) structure in any binary arithmetic domain is disclosed. The subtle rules on how the cycles (itself and its distribution) change with the arithmetic precision$e$eare elaborately investigated and proved. The regular and beautiful patterns of Cat map demonstrated in a computer adopting fixed-point arithmetics are rigorously proved and experimentally verified. The results can serve as a benchmark for studying the dynamics of the variants of the Cat map in any domain. In addition, the used methodology can be used to evaluate randomness of PRBS generated by iterating any other maps.

Incorporating deep neural networks in image compressive sensing (CS) receives intensive attentions in multimedia technology and applications recently. As deep network approaches learn the inverse mapping directly from the CS measurements, the reconstruction speed is significantly faster than the conventional CS algorithms. However, for existing network-based approaches, a CS sampling procedure has to map a separate network model. This may potentially degrade the performance of image CS with block-wise sampling because of blocking artifacts, especially when multiple sampling rates are assigned to different blocks within an image. In this paper, we develop a multi-channel deep network for block-based image CS by exploiting inter-block correlation with performance significantly exceeding the current state-of-the-art methods. The significant performance improvement is attributed to block-wise approximation but full-image removal of blocking artifacts. Specifically, with our multi-channel structure, the image blocks with a variety of sampling rates can be reconstructed in a single model. The initially reconstructed blocks are then capable of being reassembled into a full image to improve the recovered images by unrolling a hand-designed block-based CS recovery algorithm. Experimental results demonstrate that the proposed method outperforms the state-of-the-art CS methods by a large margin in terms of objective metrics and subjective visual image quality. Our source codes are available athttps://github.com/siwangzhou/DeepBCS.

When implemented in the digital domain with time, space and value discretized in the binary form, many good dynamical properties of chaotic systems in continuous domain may be degraded or even diminish. To measure the dynamic complexity of a digital chaotic system, the dynamics can be transformed to the form of a state-mapping network. Then, the parameters of the network are verified by some typical dynamical metrics of the original chaotic system in infinite precision, such as Lyapunov exponent and entropy. This article reviews some representative works on the network-based analysis of digital chaotic dynamics and presents a general framework for such analysis, unveiling some intrinsic relationships between digital chaos and complex networks. As an example for discussion, the dynamics of a state-mapping network of the Logistic map in a fixed-precision computer is analyzed and discussed.

Generating chaotic maps with expected dynamics of users is a challenging topic. Utilizing the inherent relation between the Lyapunov exponents (LEs) of the Cat map and its associated Cat matrix, this paper proposes a simple but efficient method to construct an -dimensional ( -D) hyperchaotic Cat map (HCM) with any desired number of positive LEs. The method first generates two basic -D Cat matrices iteratively and then constructs the final -D Cat matrix by performing similarity transformation on one basic -D Cat matrix by the other. Given any number of positive LEs, it can generate an -D HCM with desired hyperchaotic complexity. Two illustrative examples of -D HCMs were constructed to show the effectiveness of the proposed method, and to verify the inherent relation between the LEs and Cat matrix. Theoretical analysis proves that the parameter space of the generated HCM is very large. Performance evaluations show that, compared with existing methods, the proposed method can construct -D HCMs with lower computation complexity and their outputs demonstrate strong randomness and complex ergodicity.

A discrete cosine transform (DCT)-based no-reference video quality prediction model is proposed that measures artifacts and analyzes the statistics of compressed natural videos. The model has two stages: 1) distortion measurement and 2) nonlinear mapping. In the first stage, an unsigned ac band, three frequency bands, and two orientation bands are generated from the DCT coefficients of each decoded frame in a video sequence. Six efficient frame-level features are then extracted to quantify the distortion of natural scenes. In the second stage, each frame-level feature of all frames is transformed to a corresponding video-level feature via a temporal pooling, then a trained multilayer neural network takes all video-level features as inputs and outputs, a score as the predicted quality of the video sequence. The proposed method was tested on videos with various compression types, content, and resolution in four databases. We compared our model with a linear model, a support-vector-regression-based model, a state-of-the-art training-based model, and a four popular full-reference metrics. Detailed experimental results demonstrate that the results of the proposed method are highly correlated with the subjective assessments.

This paper re-evaluates the security of a secure Lempel-Ziv-Welch (LZW) algorithm proposed at ICME'2008. A chosen-plaintext attack is proposed to break all ciphertext indices corresponding to single-symbol dictionary entries. For short plaintexts the chosen-plaintext attack works well because string-symbol strings appear very frequently. The number of required chosen plaintexts is at the order of the alphabet size. The complexity of the chosen-plaintext attack is O(ML), where M is the number of chosen plaintexts and L is the size of the ciphertext. The chosen-plaintext attack can also be generalized to chosen-ciphertext attack. In addition to the security problem, we point out that the secure LZW algorithm has a lower compression efficiency compared with the original LZW algorithm. Finally we propose several enhancements to the secure LZW algorithm under study.

Recently four chaos-based image encryption schemes were proposed. Essentially, the four schemes can be classified into one, which is composed of two basic parts: permutation of positions and diffusion of pixel values with the same cipher-text feedback function. The operations involved in the two basic parts are determined by a pseudo random number sequence (PRNS) generated from iterating a chaotic dynamic system. According to the security requirement, the two basic parts are performed alternatively for some rounds. Despite the claim that the schemes are of high quality, we found the following security problems: 1) the schemes are not sensitive to the changes of plain-images; 2) the schemes are not sensitive to the changes of the key streams generated by any secret key; 3) there exists a serious flaw of the diffusion function; 4) the schemes can be broken with no more than [logL(MN)] + 3 chosen-images when only one iteration is used, where MN is the size of the plain- image and L is the number of different pixel values. Moreover, we found that the cryptanalysis on one of these schemes proposed by another research group is quite questionable.

Recently, a new image scrambling (i.e., encryption) scheme without bandwidth expansion was proposed based on two-dimensional discrete prolate spheroidal sequences. A comprehensive cryptanalysis is given here on this image scrambling scheme, showing that it is not sufficiently secure against various cryptographical attacks including ciphertext-only attack, known/chosen-plaintext attack, and chosen-ciphertext attack. Detailed cryptanalytic results suggest that the image scrambling scheme can only be used to realize perceptual encryption but not to provide content protection for digital images.