Search Results (290)

This paper introduces a robust and imperceptible video watermarking framework designed for blind extraction in dynamic video environments. The proposed method operates in the spatial domain and combines multiscale perceptual analysis, adaptive Just Noticeable Difference (JND)-based quantization, and temporal redundancy via multiframe embedding. Watermark bits are embedded selectively in blocks with high perceptual masking using a QIM strategy, and the corresponding DCT coefficients are estimated directly from the spatial domain to reduce complexity. To enhance resilience, each bit is redundantly inserted across multiple keyframes selected based on scene transitions. Extensive simulations over 21 benchmark videos (CIF, 4CIF, HD) validate that the method achieves superior performance in robustness and perceptual quality, with an average Bit Error Rate (BER) of 1.03%, PSNR of 50.1 dB, SSIM of 0.996, and VMAF of 97.3 under compression, noise, cropping, and temporal desynchronization. The system outperforms several recent state-of-the-art techniques in both quality and speed, requiring no access to the original video during extraction. These results confirm the method’s viability for practical applications such as copyright protection and secure video streaming. Full article

In this paper, a security-enhanced three-dimensional (3D) image hiding and encryption method is proposed by combining a layer-based phase-only hologram (POH) under structured light illumination with chaotic encryption and digital image watermarking technology. In the proposed method, the original 3D plaintext image is firstly encoded into a layer-based POH and then further encrypted into an encrypted phase with the help of a chaotic random phase mask (CRPM). Subsequently, the encrypted phase is embedded into a visible ciphertext image by using a digital image watermarking technology based on discrete wavelet transform (DWT) and singular value decomposition (SVD), leading to a 3D image hiding with high security and concealment. The encoding of POH and the utilization of CRPM can substantially enhance the level of security, and the DWT-SVD-based digital image watermarking can effectively hide the information of the 3D plaintext image in a visible ciphertext image, thus improving the imperceptibility of valid information. It is worth noting that the adopted structured light during the POH encoding possesses many optical parameters, which are all served as the supplementary keys, bringing about a great expansion of key space; meanwhile, the sensitivities of the wavelength key and singular matrix keys are also substantially enhanced thanks to the introduction of structured light, contributing to a significant enhancement of security. Numerical simulations are performed to demonstrate the feasibility of the proposed 3D image hiding method, and the simulation results show that the proposed method exhibits high feasibility and apparent security-enhanced effect as well as strong robustness. Full article

Automatic Speaker Verification (ASV) systems are increasingly employed to secure access to services and facilities. However, recent advances in speech deepfake generation pose serious threats to their reliability. Modern speech synthesis models can convincingly imitate a target speaker’s voice and generate realistic synthetic audio, potentially enabling unauthorized access through ASV systems. To counter these threats, forensic detectors have been developed to distinguish between real and fake speech. Although these models achieve strong performance, their deep learning nature makes them susceptible to adversarial attacks, i.e., carefully crafted, imperceptible perturbations in the audio signal that make the model unable to classify correctly. In this paper, we explore adversarial attacks targeting speech deepfake detectors. Specifically, we analyze the effectiveness of Basic Iterative Method (BIM) attacks applied in both time and frequency domains under white- and black-box conditions. Additionally, we propose an ensemble-based attack strategy designed to simultaneously target multiple detection models. This approach generates adversarial examples with balanced effectiveness across the ensemble, enhancing transferability to unseen models. Our experimental results show that, although crafting universally transferable attacks remains challenging, it is possible to fool state-of-the-art detectors using minimal, imperceptible perturbations, highlighting the need for more robust defenses in speech deepfake detection. Full article

Large language models (LLMs) pose significant challenges to content authentication, as their sophisticated generation capabilities make distinguishing AI-produced text from human writing increasingly difficult. Current detection methods suffer from limited information capture, poor rate–distortion trade-offs, and vulnerability to adversarial perturbations. We present CurveMark, a novel dual-channel detection framework that combines probability curvature analysis with dynamic semantic watermarking, grounded in information-theoretic principles to maximize mutual information between text sources and observable features. To address the limitation of requiring prior knowledge of source models, we incorporate a Bayesian multi-hypothesis detection framework for statistical inference without prior assumptions. Our approach embeds imperceptible watermarks during generation via entropy-aware, semantically informed token selection and extracts complementary features from probability curvature patterns and watermark-specific metrics. Evaluation across multiple datasets and LLM architectures demonstrates 95.4% detection accuracy with minimal quality degradation (perplexity increase < 1.3), achieving 85–89% channel capacity utilization and robust performance under adversarial perturbations (72–94% information retention). Full article

Linguistic steganography can be utilized to establish covert communication channels on social media platforms, thus facilitating the dissemination of illegal messages, seriously compromising cyberspace security. Synonym substitution-based linguistic steganography methods have garnered considerable attention due to their simplicity and strong imperceptibility. Existing linguistic steganalysis methods have not achieved excellent detection performance for the aforementioned type of linguistic steganography. In this paper, based on the idea of focusing on accumulated differences, we propose a two-stage synonym substitution-based linguistic steganalysis method that does not require a synonym database and can effectively detect texts with very low embedding rates. Experimental results demonstrate that this method achieves an average detection accuracy 2.4% higher than the comparative method. Full article

The widespread deployment of large language models (LLMs) has raised urgent demands for verifiable content attribution and misuse mitigation. Existing text watermarking techniques often struggle in black-box or sampling-based scenarios due to limitations in robustness, imperceptibility, and detection generality. These challenges are particularly critical in open-access settings, where model internals and generation logits are unavailable for attribution. To address these limitations, we propose CWS (Contrastive Watermarking with Semantic Modeling)—a novel keyless watermarking framework that integrates contrastive semantic token selection and shared embedding space alignment. CWS enables context-aware, fluent watermark embedding while supporting robust detection via a dual-branch mechanism: a lightweight z-score statistical test for public verification and a GRU-based semantic decoder for black-box adversarial robustness. Experiments on GPT-2, OPT-1.3B, and LLaMA-7B over C4 and DBpedia datasets demonstrate that CWS achieves F1 scores up to 99.9% and maintains F1 ≥ 93% under semantic rewriting, token substitution, and lossy compression (ε ≤ 0.25, δ ≤ 0.2). The GRU-based detector offers a superior speed–accuracy trade-off (0.42 s/sample) over LSTM and Transformer baselines. These results highlight CWS as a lightweight, black-box-compatible, and semantically robust watermarking method suitable for practical content attribution across LLM architectures and decoding strategies. Furthermore, CWS maintains a symmetrical architecture between embedding and detection stages via shared semantic representations, ensuring structural consistency and robustness. This semantic symmetry helps preserve detection reliability across diverse decoding strategies and adversarial conditions. Full article

Steganography has long served as a powerful tool for covert communication, particularly through image-based techniques that embed secret information within innocuous cover images. With the increasing adoption of deep learning, researchers have sought more secure and efficient methods for image steganography. This study builds upon and extends the DeepWaveletFusion approach by integrating convolutional neural networks (CNNs) with the discrete wavelet transform (DWT) to enhance both embedding and recovery performance. The proposed method, DeepWaveletFusionToo, is a lightweight architecture that employs a custom-built DWT image dataset and leverages the mean squared error (MSE) loss function during training, significantly reducing model complexity and computational cost. Experimental results demonstrate that DeepWaveletFusionToo achieves improved imperceptibility compared to its predecessor and delivers competitive recovery accuracy over existing deep learning-based steganographic techniques, establishing its simplicity and effectiveness. Full article

The swift advancement of information and communication technology has made it increasingly difficult to guarantee the security of transmitted data. Traditional encryption techniques, particularly in multimedia applications, frequently fail to defend against sophisticated attacks, such as chosen-plaintext, differential, and statistical analysis attacks. More often than not, traditional cryptographic methods lack proper diffusion and sufficient randomness, which is why they are vulnerable to these types of attacks. By combining multi-level chaotic maps with Least Significant Bit (LSB) steganography and Advanced Encryption Standard (AES) encryption, this study proposes an improved security approach for picture transmission. A hybrid chaotic system dynamically creates the encryption keys, guaranteeing high unpredictability and resistance to brute-force attacks. Next, it incorporates the encrypted images into video frames, making it challenging to find the secret data. The suggested method demonstrates its resilience to statistical attacks by achieving entropy values over 7.99 and number of pixels change rate (NPCR) values above 99.63% in contrast to traditional encryption techniques, showing how resilient it is to statistical attacks. Our hybrid approach improves data secrecy and resistance to various cryptographic attacks. Experimental results confirm the efficiency of the suggested technique by achieving entropy values around 7.99, number of pixels change rate (NPCR) values above 99.63%, and unified average changing intensity (UACI) values over 31.98%, ensuring the secure transmission of sensitive images while maintaining video imperceptibility. Full article

The new generation of food packaging should not only be biodegradable, but also provide additional protective properties for packaged products, extending their shelf life. In this paper, we present the results of research on cast-extruded poly(butylene succinate) (PBS) films coated with hydroxypropyl methylcellulose (HPMC) modified with CO₂ extract from sea buckthorn (ES) or its ethosomes (ET) at amounts of 1 or 5 pph per HPMC. In addition, the developed films were exposed to accelerated aging (UV radiation and elevated temperature) to determine its effect on the films’ properties. Based on SEM, it can be concluded that accelerated aging results in the uncovering of the extract and ethosomes from the coating’s bulk. GPC showed a decrease in the molecular weight of PBS after treatment, additionally amplified by the presence of HPMC. However, the addition of ES or ET in low concentrations reduced the level of polyester degradation. The presence of the modified coating and its treatment increased the oxygen barrier (a decrease from 324 cm³/m² × 24 h for neat PBS to 208 cm³/m² × 24 h for the coated and modified PBS ET5). Despite the presence of colored extract or ethosomes in the coating, the color differences compared with neat PBS were imperceptible (ΔE < 1). The addition of 5 pph of sea buckthorn extract or its ethosomes in combination with accelerated aging resulted in the complete inhibition of the growth of E. coli and S. aureus, which was not observed in non-aged samples. The results obtained demonstrate an improvement in bioactive properties and protection against the negative effects of UV radiation on the film due to the presence of ET or ES in the coating. The developed systems could be used in the food industry as active packaging. Full article

Background/Objectives: Diabetic retinopathy (DR) remains one of the primary causes of preventable vision impairment worldwide, particularly among individuals with long-standing diabetes. The progressive damage of retinal microvasculature can lead to irreversible blindness if not detected and managed at an early stage. Therefore, the development of reliable, non-invasive, and automated screening tools has become increasingly vital in modern ophthalmology. With the evolution of medical imaging technologies, Optical Coherence Tomography (OCT) has emerged as a valuable modality for capturing high-resolution cross-sectional images of retinal structures. In parallel, machine learning has shown considerable promise in supporting early disease recognition by uncovering complex and often imperceptible patterns in image data. Methods: This study introduces a novel framework for the early detection of DR through multifractal analysis of OCT images. Multifractal features, extracted using a box-counting approach, provide quantitative descriptors that reflect the structural irregularities of retinal tissue associated with pathological changes. Results: A comparative evaluation of several machine learning algorithms was conducted to assess classification performance. Among them, the Multi-Layer Perceptron (MLP) achieved the highest predictive accuracy, with a score of $98.02\%$, along with precision, recall, and F1-score values of $98.24\%$, $97.80\%$, and $98.01\%$, respectively. Conclusions: These results highlight the strength of combining OCT imaging with multifractal geometry and deep learning methods to build robust and scalable systems for DR screening. The proposed approach could contribute significantly to improving early diagnosis, clinical decision-making, and patient outcomes in diabetic eye care. Full article

In this work, we propose the integration of a mechanism to enable smooth transitions between different locomotion patterns in a hexapod robot. Specifically, we utilize a spiking neural network (SNN) functioning as a Central Pattern Generator (CPG) to generate three distinct locomotion patterns, or gaits: walk, jog, and run. This network produces coordinated spike trains, mimicking those generated in the brain, which are translated into synchronized robot movements via PWM signals. Subsequently, these spike trains are compared using a similarity metric known as SPIKE-synchronization to identify the optimal point for transitioning from one gait to another. This approach aims to achieve three main objectives: first, to maintain the robot’s balance during transitions; second, to ensure that gait transitions are almost imperceptible; and third, to improve energy efficiency by reducing abrupt changes in the robot’s actuators (servomotors). To validate our proposal, we incorporated FSR sensors on the robot’s legs to detect the rigidity of the terrain it navigates. Based on the terrain’s rigidity, the robot dynamically transitions between gaits. The system was tested in real time on a physical hexapod robot across four different types of terrain. Although the method was validated exclusively on a hexapod robot, it can be extended to any legged robot. Full article

Infrared (IR) images record the temperature radiation distribution of the object being captured. The hue and color difference in the image reflect the caloric and temperature difference, respectively. However, due to the thermal diffusion effect, the target information in IR images can be relatively large and the objects’ boundaries are blurred. Therefore, IR images may undergo some image enhancement operations prior to use in relevant application scenarios. Furthermore, Infrared Enhancement (IRE) algorithms have a negative impact on the watermarking information embedded into the IR image in most cases. In this paper, we propose a novel multi-scale robust watermarking model under IRE attack, called IEWNet. This model trains a preprocessing module for extracting image features based on the conventional Undecimated Dual Tree Complex Wavelet Transform (UDTCWT). Furthermore, we consider developing a noise layer with a focus on four deep learning and eight classical attacks, and all of these attacks are based on IRE algorithms. Moreover, we add a noise layer or an enhancement module between the encoder and decoder according to the application scenarios. The results of the imperceptibility experiments on six public datasets prove that the Peak Signal to Noise Ratio (PSNR) is usually higher than 40 dB. The robustness of the algorithms is also better than the existing state-of-the-art image watermarking algorithms used in the performance evaluation comparison. Full article

Cervical cancer is one of the most common malignant tumors, with high incidence and mortality rates. Recent studies mainly adopt Artificial Intelligence (AI) models to detect cervical cells. Yet, due to the imperceptible symptoms of cervical cells, there are three problems that may hinder the performance of the existing approaches: (a) poor quality of the whole-slide image (WSI) performed on cervical cells may lead to undesirable performance; (b) several types of abnormal cervical cells are involved in the progression of cervical cells from normal to cancer, which requires extensive clinical data for training; and (c) the diagnosis of the WSI is medical-rule-driven and requires the AI model to provide interpretability. To address these issues, we propose an integrated automatic cervical cancer screening (IACCS) framework. First, the IACCS framework incorporates a quality assessment module utilizing binarization-based cell counting and a Support Vector Machine (SVM) approach to identify fuzzy regions, ensuring WSI suitability for analysis. Second, to overcome the data limitations, the framework employs data enhancement techniques alongside incremental learning (IL) and active learning (AL) mechanisms, allowing the model to adapt progressively and learn efficiently from new data and expert feedback. Third, recognizing the need for interpretability, the diagnostic decision process is modeled as a multi-objective optimization problem. A multi-objective optimization algorithm is used to generate a set of interpretable diagnostic rules that offer explicit trade-offs between sensitivity and specificity. Extensive experiments demonstrate the effectiveness of the proposed IACCS framework. Applying our comprehensive framework yielded significant improvements in detection accuracy, achieving, for example, a 6.34% increase in mAP_50:95 compared to the baseline YOLOv8 model. Furthermore, the generated Pareto-optimal diagnostic rules provide superior and more flexible diagnostic options compared to traditional manually defined rules. This research presents a validated pathway towards more robust, adaptable, and interpretable AI-assisted cervical cancer screening. Full article

Neuronal apoptosis is an early and critical pathological hallmark of many chronic neurodegenerative diseases, often occurring silently long before the appearance of overt clinical symptoms. In this study, we engineered astrocytes utilizing a dual-biomarker recognition synNotch system (dual-synNotch). This system is designed to specifically identify neuronal apoptosis through the ‘AND Gate’ activation mechanism, which is triggered by the simultaneous sensing of the apoptotic signal phosphatidylserine (PS) and the neuronal signal ganglioside Gt1b. Upon detection of these neuronal apoptotic signals, the synNotch receptors are activated, inducing the expression of two key molecules: secreted Gaussia luciferase (GLuc), a highly detectable reporter that can cross the blood–brain barrier (BBB), and brain-derived neurotrophic factor (BDNF), a neuroprotective molecule that promotes neuronal survival by inhibiting apoptosis and enhancing memory and cognitive function. This engineered system effectively converts and amplifies early, imperceptible neuronal apoptotic signals into detectable outputs, enabling convenient in vitro monitoring and diagnosis. Therefore, it represents a promising strategy for the early detection and intervention of neurodegenerative diseases associated with neuronal apoptosis. Full article

Ensuring the security of remote sensing images is essential to prevent unauthorized access, tampering, and misuse. Deep learning-based digital watermarking offers a promising solution by embedding imperceptible information to protect data integrity. This paper proposes SIR-DCGAN, an attention-guided robust watermarking method for remote sensing image protection. It incorporates an IR-FFM feature fusion module to enhance feature reuse across different layers and an SE-AM attention mechanism to emphasize critical watermark features. Additionally, a noise simulation sub-network is introduced to improve resistance against common and combined attacks. The proposed method achieves high imperceptibility and robustness while maintaining low computational cost. Extensive experiments on both remote sensing and natural image datasets validate its effectiveness, with performance consistently surpassing existing approaches. These results demonstrate the practicality and reliability of SIR-DCGAN for secure image distribution and copyright protection. Full article