Image Coding Research Articles

Robust steganographic framework for securing sensitive healthcare data of telemedicine using convolutional neural network

AbstractData is the key element that runs the modern society. Large amounts of data are being released day by day as a result of many activities. The digital data is transferred through the Internet which may be vulnerable to attacks while transmitting. Especially, the medical data is observed to be of at most importance. Thus, the security of the data should be preserved while communicating through the Internet. Many techniques have been evolved for securing the data, such as Encryption which makes the data not understandable by others and techniques such as Steganography, which hides the data inside other file or document. Traditional methods of Steganography‐like LSB substitution are subjected to risks of manipulation of carrier image and poor embedding capabilities. In light of this, the authors introduce a Convolutional Neural Network‐based image steganography method that operates on DICOM images which conceals the sensitive medical data in the carrier file, thereby increasing the privacy of the sensitive data. The data considered here is brain MRI scan images. The Prep Net, Hiding Net and Reveal Net networks, each with distinct number of convolution layers are used to build the model. The sensitive data is firstly segmented to detect the Region of Interest (ROI) and then the combination of sensitive data and the carrier image are fed to the Prep Net to manipulate sensitive images in such a form that it can easily fit inside the carrier image. The Hiding Net takes the result of Prep Net and embeds the sensitive image inside the carrier image to form a stego image. The Reveal Net takes the result of Hiding Net image and then extracts the sensitive image with minimal loss. The dataset contains medical images of DICOM format taken from open source platform Kaggle that contains 3500 images of 2 classes. The results obtained show that the proposed model achieves 20 percent better output compared to traditional LSB methods. As a result, the potential for hiding the data will be expanded, as well as its security.

Optimizing Digital Image Steganography to Enhance the Security of Secret Message Delivery

Image steganography is a technique used to hide secret messages in image media. In this research, 2 method improvements are proposed, namely (1) layered message security utilizing vigenere encryption with asymmetric keys, and (2) optimizing the hiding capacity (HC) of secret messages, utilizing the bit shift operation method. From the test results it can be proven that layered message security has been successfully implemented, and the capacity of secret messages can be increased. From the initial 4 bits per pixel it increased to 8 bits per pixel. However, the steganography image quality of the proposed method is not better than the PVDMF method.

Lithium-ion battery state of health prognostication employing multi-model fusion approach based on image coding of charging voltage and temperature data

The employment of readily obtainable parameters, including voltage and temperature, derived from the battery management system facilitates the real-time evaluation of lithium-ion batteries health status. However, the complex aging mechanisms and noise interference inherent in lithium-ion batteries present substantial challenges to accurate estimation. Hence, this research proposes a multi-model fusion approach utilizing Gramian Angular Field encoding to accurately predict the health status of lithium-ion batteries. Battery voltage and temperature data are acquired through system aging experiments. The Gramian Angular Field-based image encoding transforms these data into images, accentuating the subtle characteristics of the data and thereby enhancing its recognizability by neural networks. Subsequently, two-dimensional Convolutional Neural Networks are employed to extract features from the images, followed by one-dimensional Convolutional Neural Networks to reduce the dimensions of the feature matrix. The battery health status is then predicted utilizing Long Short-term Memory Networks. The culmination is the evaluation of the model performance through the application of quantitative error metrics. The study results show that the method can pinpoint the prediction error to within 2%, significantly improving accuracy over traditional prediction methods. It proves the great potential of direct data, such as voltage and temperature, in predicting battery health.

Moiré pattern generation-based image steganography

Generative steganography has developed recently due to its high resistance against steganalysis detection. It usually synthesizes stego images directly from secret information. In contrast to this manner, we propose a generative steganographic scheme by synthesizing Moiré patterns in this paper. Moiré patterns are widely observed in captured photos. They present various shapes, colors, and frequency ranges, which are expected to help carry secret information robustly and securely. The scheme synthesizes Moiré patterns via a Moiré pattern generator. Then a secret message is encoded in these patterns by a parallel encoder. The Moiré pattern generator employs a multi-branch structure to generate sub Moiré patterns at distinct frequencies. A discriminator is further imposed to ensure the realness of synthesized Moiré patterns. The parallel encoder spreads secret information over Moiré patterns in both frequency and spatial domain. A decoder and a steganalyzer are also included to ensure the robustness and undetectability of the information hiding. Furthermore, a two-stage training strategy is designed to accomplish both Moiré pattern generation and information hiding tasks. Experimental results demonstrate that the proposed scheme presents high undetectability against existing steganalytic tools, meanwhile, it can resist common image attacks such as AWGN and JPEG compression.

Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion

Deep incremental hashing has become a subject of considerable interest due to its capability to learn hash codes in an incremental manner, eliminating the need to generate codes for classes that have already been learned. However, accommodating more classes requires longer hash codes, and regenerating database codes becomes inevitable when code expansion is required. In this paper, we present a unified deep hash framework that can simultaneously learn new classes and increase hash code capacity. Specifically, we design a triple-channel asymmetric framework to optimize a new CNN model with a target code length and a code projection matrix. This enables us to directly generate hash codes for new images, and efficiently generate expanded hash codes for original database images from the old ones with the learned projection matrix. Meanwhile, we propose a pairwise-label-based incremental similarity-preserving loss to optimize the new CNN model, which can incrementally preserve new similarities while maintaining the old ones. Additionally, we design a double-end quantization loss to reduce the quantization error from new and original query images. As a result, our method efficiently embeds both new and original similarities into the expanded hash codes, while keeping the original database codes unchanged. We conduct extensive experiments on three widely-used image retrieval benchmarks, demonstrating that our method can significantly reduce the time required to expand existing database codes, while maintaining state-of-the-art retrieval performance.

StegaStyleGAN: Towards Generic and Practical Generative Image Steganography

The recent advances in generative image steganography have drawn increasing attention due to their potential for provable security and bulk embedding capacity. However, existing generative steganographic schemes are usually tailored for specific tasks and are hardly applied to applications with practical constraints. To address this issue, this paper proposes a generic generative image steganography scheme called Steganography StyleGAN (StegaStyleGAN) that meets the practical objectives of security, capacity, and robustness within the same framework. In StegaStyleGAN, a novel Distribution-Preserving Secret Data Modulator (DP-SDM) is used to achieve provably secure generative image steganography by preserving the data distribution of the model inputs. Additionally, a generic and efficient Secret Data Extractor (SDE) is invented for accurate secret data extraction. By choosing whether to incorporate the Image Attack Simulator (IAS) during the training process, one can obtain two models with different parameters but the same structure (both generator and extractor) for lossless and lossy channel covert communication, namely StegaStyleGAN-Ls and StegaStyleGAN-Ly. Furthermore, by mating with GAN inversion, conditional generative steganography can be achieved as well. Experimental results demonstrate that, whether for lossless or lossy communication channels, the proposed StegaStyleGAN can significantly outperform the corresponding state-of-the-art schemes.

Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding

While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering operations and local attention for correlation characterization and compact representation of an image. As seen, CLIC expands the receptive field into the entire image for intra-cluster feature aggregation. Afterward, features are reordered to their original spatial positions to pass through the local attention units for inter-cluster embedding. Additionally, we introduce the Guided Post-Quantization Filtering (GuidedPQF) into CLIC, effectively mitigating the propagation and accumulation of quantization errors at the initial decoding stage. Extensive experiments demonstrate the superior performance of CLIC over state-of-the-art works: when optimized using MSE, it outperforms VVC by about 10% BD-Rate in three widely-used benchmark datasets; when optimized using MS-SSIM, it saves more than 50% BD-Rate over VVC. Our CLIC offers a new way to generate compact representations for image compression, which also provides a novel direction along the line of LIC development.

Lossless image steganography: Regard steganography as super-resolution

Image steganography attempts to imperceptibly hide the secret image within the cover image. Most of the existing deep learning-based steganography approaches have excelled in payload capacity, visual quality, and steganographic security. However, they are difficult to losslessly reconstruct secret images from stego images with relatively large payload capacity. Recently, although some studies have introduced invertible neural networks (INNs) to achieve large-capacity image steganography, these methods still cannot reconstruct the secret image losslessly due to the existence of lost information on the output side of the concealing network. We present an INN-based framework in this paper for lossless image steganography. Specifically, we regard image steganography as an image super-resolution task that converts low-resolution cover images to high-resolution stego images while hiding secret images. The feature dimension of the generated stego image matches the total dimension of the input secret and cover images, thereby eliminating the lost information. Besides, a bijective secret projection module is designed to transform various secret images into a latent variable that follows a simple distribution, improving the imperceptibility of the secret image. Comprehensive experiments indicate that the proposed framework achieves secure hiding and lossless extraction of the secret image.

Bio-Inspired algorithms for secure image steganography: enhancing data security and quality in data transmission

The proliferation of data sharing over the Internet has given rise to pressing concerns surrounding data security. Addressing these concerns, steganography emerges as a viable mechanism to safeguard data during transmission. It involves concealing messages within other media, such as images, exchanged over networks. In this research, we propose an innovative image steganography approach by harnessing the capabilities of bio-inspired algorithms. A central challenge in steganography revolves around the inherent pixel correlations within cover images, which may inadvertently leak sensitive information to potential intruders. To tackle this challenge head-on, we harness the potential of bio-inspired algorithms, which have exhibited promise in efficiently mitigating these vulnerabilities. This paper introduces a steganography strategy rooted in a fusion model that seamlessly integrates diverse bio-inspired algorithms. Our novel embedding approach ensures the production of robust and high-quality cover images and disrupts bit sequences effectively, thereby enhancing resistance against potential attacks. We meticulously evaluate the performance of our method using a comprehensive dataset encompassing grayscale and JPEG color images. Our particular emphasis on color images arises from their superior capacity to conceal a greater volume of information. The results vividly demonstrate our approach's effectiveness in achieving secure and efficient data concealment within images.

Evaluation of the Progress of Coronavirus Disease-19 Pneumonia using the British Society of Thoracic Imaging Reporting Model: A Validation Study

Abstract: Background: SARS-COV-2 (also known as severe acute respiratory syndrome corona virus-2), emerged as a pandemic and became an overwhelming global concern, causing substantial morbidity and mortality worldwide. Reverse transcription polymerase chain reaction (RT-PCR) is considered a gold standard in detecting clinically symptomatic patients but can have false negative and false positive results. As chest X-Ray (CXR) is considered as a baseline investigation in many hospitals, BSTI reporting model during COVID-19 pandemic has been a useful tool in diagnosis of COVID-19 pneumonia. Objective: To validate the British Society Thoracic Imaging (BSTI) coding system in the evaluation of the progress of the disease severity in patients with coronavirus disease-2019 (COVID-19) pneumonia. Materials and Methods: This is a cross sectional observational study. Total 450 CXRs (which included both the baseline and serial CXRs) of 225 COVID positive patients (RT-PCR positive for COVID-19 on nasal swabs) were included. These were retrospectively reviewed and reported by two Radiologists (having experience of at least 5 years in Radiology Reporting) in Corona Ward in Dr. Ruth K M Pfau Civil Hospital Karachi, Pakistan, for the duration of 10 months from 1st March 2020 till 31st December 2020. BSTI coding system was used to classify and interpret the CXR imaging findings as normal, definitive, indeterminate and non-COVID for baseline (CXR on 1st day of admission) and follow up CXRs (done in between 3rd and 7th day of admission). Data was analyzed using SPSS version 25. Numeric data was assessed for distribution using Shapiro-Wilks test. Median and interquartile range (IQR) were reported for numeric variables. Frequencies and percentages were reported for categorical data. Kappa statistics was applied to assess the agreement between BSTI scoring at baseline and follow-up CXRs. A p-value ≤0.05 was considered as statistically significant. Result: CXRs (including 225 baseline and 225 follow up CXRs) of 225 RT-PCR COVID-19 positive patients were analyzed. Interval change in BSTI coding system was noted, increase in frequency of probable/definitive COVID-19 findings were diagnosed on serial CXRs. The BSTI scoring at baseline and follow-up showed moderate agreement with kappa statistics as 60.3% (p=0.001). Conclusion: BSTI coding system can be helpful to classify the COVID-19 disease on CXR and filter for the prognosis of disease severity in the serial radiographs. Utilization of BSTI reporting model for reporting CXRs, even before RT-PCR, in future COVID pandemic can be considered as a useful tool.

NAISS: A reverse proxy approach to mitigate MageCart's e-skimmers in e-commerce

The rise of payment details theft has led to increasing concerns regarding the security of e-commerce platforms. For the MageCart threat family, the attacks employ e-skimmers, which are pieces of software code that instruct clients to forward payment details to an attacker-controlled server. They can be injected into hosting providers' servers as HTML tags such as script, iframe, and img. By leveraging image steganography - the technique of hiding structured information inside images without visual perturbances - MageCart groups can deliver e-skimmers without raising suspicion. In this work, we systematically review applicable solutions in the literature and evaluate their drawbacks in the setting of a compromised hosting provider. While promising, existing solutions in the literature present shortcomings such as a lack of compatibility, adaptability, or functionality in the presence of an attacker. Based on this review, we compile a set of features for a better solution, which we use as a foundation for designing our proposed solution - NAISS: Network Authentication of Images to Stop e-Skimmers. Through our solution, digital signatures of individual images are checked inside a server-side middlebox residing in the hosting provider's network to prevent the transmission of unauthorized images to clients. Elliptic curve signatures are provided by the e-commerce platform developer prior to uploading a website to the hosting provider. Our proof-of-concept implementation shows that NAISS is capable of filtering 100% of present stegoimages, regardless of their novelty, while imposing a minimal performance detriment and no client-side modifications.

Enhancing Security through Advanced Image Steganography Techniques

The project aims to explore various types of steganography techniques, with a focus on image steganography, where information is concealed within images. This involves decrypting the hidden data to retrieve the message image, a process that can be achieved through different methods. The study delves into image steganography, which involves hiding information such as text, images, or audio files within other image or video files. Specifically, the project concentrates on utilizing steganography to embed an image within another image using spatial domain techniques. By examining this particular method, the project seeks to deepen understanding of how image steganography operates and its potential applications. This research contributes to the field by providing insights into the implementation and effectiveness of steganography techniques, offering valuable knowledge for information security and data protection purposes. Through practical demonstrations and analysis, the project aims to showcase the capabilities and limitations of image steganography, facilitating further research and development in this domain. Ultimately, the project endeavors to enhance comprehension of steganography methods and their significance in safeguarding digital information

Parallel BFS through pennant data structure with reducer hyper‐object based data hiding for 3D mesh images

AbstractData hiding refers to the technique employed to conceal sensitive data within various forms of multimedia, such as video, audio, text, 2D images, 3D images, and more, while also being able to successfully extract said information from the multimedia file. Although numerous data hiding techniques exist for 2D images, research on data hiding in 3D images is still in its early stages. Current 3D image steganography methods suffer from limitations in terms of embedding capacity and time complexity. To overcome these difficulties, we propose a novel 3D image steganographic technique using Parallel Breadth First Search (PBFS) with hyper‐object. Our approach utilizes the PBFS searching strategy, along with layer synchronization, to embed private information within the vertices of the 3D mesh images. To maximize the effectiveness of the process and minimize time, cost, complexity, and execution, we involved the data structure “bag” to parallelize the BFS. The implementation of bags is based on the pennant data structure. This methodology obtained an impressive Embedding Capacity (EC) of 9.00 bits per vertex (bpv) while maintaining superior visual quality and time complexity. Consequently, the proposed methodology holds great potential for widespread utilization across numerous sectors, including private and government organizations such as intelligence agencies, intellectual property rights management, cloud data security, defense, covert communication, medical imagery, and more.

Low-value MRI of the knee in Norway: a register-based study to identify the proportion of potentially low-value MRIs and estimate the related costs

ObjectivesThe objective of this study is to investigate the proportion of potentially low-value knee MRI in Norway and to provide an estimate of the related costs.DesignRegister study based on conditional...

Payload-Independent Direct Cost Learning for Image Steganography

Payload-Independent Direct Cost Learning for Image Steganography

Hybrid Edge Detection Methods in Image Steganography for High Embedding Capacity

Abstract In this research, we propose two new image steganography techniques focusing on increasing image-embedding capacity. The methods will encrypt and hide secret information in the edge area. We utilized two hybrid methods for the edge detection of the images. The first method combines the Laplacian of Gaussian (LoG) with the wavelet transform algorithm and the second method mixes the LOG and Canny. The Combining was performed using addWeighted. The text message will be encrypted using the GIFT cipher method for further security and low computation. For the effectiveness evaluation of the proposed method, various evaluation metrics were used such as embedding capacity, PSNR, MSE, and SSIM. The obtained results indicate that the proposed method has a greater embedding capacity in comparison with other methods, while still maintaining high levels of imperceptibility in the cover image.

Correction to: Image Steganography Method for Securing Multiple Images Using LSB–GA

Correction to: Image Steganography Method for Securing Multiple Images Using LSB–GA

Automating The Deployment of MERN Stack on AWS App Runner Using AWS Code Pipeline

This paper explores the deployment of web applications utilizing AWS App Runner, a managed platform that simplifies the deployment process by allowing developers to select runtimes and deploy applications without the need for extensive configuration. It focuses on the advantages of using Docker runtime for API execution and web application deployment, highlighting the ease of dockerizing applications and the seamless integration with Amazon Elastic Container Registry (ECR). ECR provides a fully-managed Docker container registry, facilitating the efficient storage, management, and deployment of Docker container images. Additionally, the paper discusses the role of AWS CodeCommit as a secure, scalable, managed source control service for hosting private Git repositories, emphasizing its significance in the deployment pipeline. The combined use of these AWS services offers a streamlined, costeffective solution for deploying scalable and secure web applications directly from source code or container images to the AWS Cloud, thereby enhancing the deployment process for developers.

Strengthening wavelet based image steganography using Rubik’s cube segmentation and secret image scrambling

Strengthening wavelet based image steganography using Rubik’s cube segmentation and secret image scrambling

Image Steganography Based on Hybrid Salp Swarm Algorithm and Particle Swarm Optimization

Image Steganography Based on Hybrid Salp Swarm Algorithm and Particle Swarm Optimization