Reversible Watermarking Techniques

Digital content security gained immense attention over past two decades due rapid digitization of industries and government sectors, and providing security to digital content became a vital challenge. Digital watermarking is one prominent solution to protect digital content from tamper detection and content authentication. However, digital watermarking can alter sensitive information present on cover-content during embedding, then the recovery of exact cover-content may not be possible during extraction process. Moreover, certain applications may not allow small distortions in cover-content. Hence, reversible watermarking techniques of digital content can extract cover-content and watermark completely. Additionally, reversible watermarking is gaining popularity by an increasing number of applications in military, law enforcement, healthcare. In this chapter, the authors compare and contrast the different reversible watermarking techniques with quality and embedding capacity parameters. This survey is essential due to the rapid evolution of reversible watermarking techniques.

Applying Smart Security Model to Protect Client Services From the Threats of the Optical Network

The chapter discusses the security of the client signals over the optical network from any wiretapping or loosing. The physical layer of the optical transport network (OTN) is the weakest layer in the network; anyone can access the optical cables from any location and states his attack. A security layer is proposed to be added in the mapping of OTN frames. The detection of any intrusion is done by monitoring the variations in the optical signal to noise ratio (OSNR) by using intelligent software defined network. The signal cryptographic is done at the source and the destination only. The chapter shows how the multi-failure restorations in the multi-domains could be done. A new model is introduced by slicing the multi-domains to three layers to fit the needs of 5G. The results show that the multi-failure restoration improved from 25% to 100%, the revenue from some OTN domains increased by 50%, the switching time enhanced by 50%, the latency reduced from 27 msec to 742 usec, and it will take many years to figure out the right keys to perform the decryption process.

Building an IPFS and Blockchain-Based Decentralized Storage Model for Medical Imaging

Currently, sharing and access of medical imaging is a significant element of present healthcare systems, but the existing infrastructure of medical image sharing depends on third-party approval. In this chapter, the authors have proposed a framework in order to provide a decentralized storage model for medical image sharing through IPFS and blockchain technology that remove the hurdle of third-party dependency. In the proposed model, the authors are sharing the imaging and communications in medicine (DICOM) medical images, which consist of various information related to disease, and hence, the framework can be utilized in the real-time application of the healthcare system. Moreover, the framework maintains the feature of immutability, privacy, and availability of information owing to the blockchain-based decentralized storage model. Furthermore, the authors have also discussed how the information can be accessed by the peers in the blockchain network with the help of consensus. To implement the framework, they have used the python ask and anaconda python.

Detection of DDoS Attack Using Naive Bayes Classifier

Naive Bayes classifiers are a set of categorization techniques based on Bayes' theorem. It is a collection of algorithms where all these algorithms share a common principle. This chapter presents the detection of DDos attack using scoreboard dataset. The dataset is separated into two parts, that is, feature vector and the reaction vector. Feature vector contains all the rows of dataset in which each vector consists of the value of dependent features such as IP address, port, counter, flag, syncnt, no. of packets, etc. The reaction vector contains the value of class variable (prediction or output) for each row. Result shows the effectiveness of the model in preventing DDoS attack by classifying request.

Time Series Analysis for Crime Forecasting Using ARIMA (Autoregressive Integrated Moving Average) Model

With massive advancements in the fields of data analysis and data mining, a new importance has been gained by data visualization. Data visualization focuses on visualizing and abstracting complex data to make it comprehensible and easy to understand using visual representation of information. Analysis of crime and crime-related data has been steadily popularizing over the last decade, and this chapter aims at visualizing such data. Crime data for several different types of crime for many countries in the world has been collected, compiled, processed, analyzed, and visualized in this chapter. Predictive analysis of this data has also been performed using time series analysis. This chapter aims to create a hub where internet users can easily view and interpret this data.

Evolution of Big Data in Medical Imaging Modalities to Extract Features Using Region Growing Segmentation, GLCM, and Discrete Wavelet Transform

Big data refers to the massive amount of data from sundry sources (gregarious media, healthcare, different sensor, etc.) with very high velocity. Due to expeditious growth, the multimedia or image data has rapidly incremented due to the expansion of convivial networking, surveillance cameras, satellite images, and medical images. Healthcare is the most promising area where big data can be applied to make a vicissitude in human life. The process for analyzing the intricate data is mundanely concerned with the disclosing of hidden patterns. In healthcare fields capturing the visual context of any medical images, extraction is a well introduced word in digital image processing. The motive of this research is to present a detailed overview of big data in healthcare and processing of non-invasive medical images with the avail of feature extraction techniques such as region growing segmentation, GLCM, and discrete wavelet transform.

A Machine Learning Approach for Anomaly Detection to Secure Smart Grid Systems

The rapid industrial growth in cyber-physical systems has led to upgradation of the traditional power grid into a network communication infrastructure. The benefits of integrating smart components have brought about security issues as attack perimeter has increased. In this chapter, firstly, the authors train the network on the results generated by the uncompromised grid network result dataset and then extract valuable features by the various system calls made by the kernel on the grid and after that internal operations being performed. Analyzing the metrics and predicting how the call lists are differing in call types, parameters being passed to the OS, the size of the system calls, and return values of the calls of both the systems and identifying benign devices from the compromised ones in the test bed are done. Predictions can be accurately made on the device behavior in the smart grid and calculating the efficiency of correct detection vs. false detection according to the confusion matrix, and finally, accuracy and F-score will be computed against successful anomaly detection behavior.

Noise Removal With Filtering Techniques

An overview of the image noise models and the de-noising techniques available are presented here. Basically, filtering is one of the de-noising approaches that is normally performed in both spatial and frequency domains. Thus, this chapter focuses on these two approaches. Few filters like mean, median, sharpening, and adaptive median filter are discussed under spatial domain. In the frequency domain, as Butterworth filter suits better for images, Butterworth low pass, high pass, and band pass filters along with homomorphic filters are also analyzed. It also provides a comparative analysis of these approaches for both synthetic and medical images with some performance measures.

Video Classification Using 3D Convolutional Neural Network

Since video includes both temporal and spatial features, it has become a fascinating classification problem. Each frame within a video holds important information called spatial information, as does the context of that frame relative to the frames before it in time called temporal information. Several methods have been invented for video classification, but each one is suffering from its own drawback. One of such method is called convolutional neural networks (CNN) model. It is a category of deep learning neural network model that can turn directly on the underdone inputs. However, such models are recently limited to handling two-dimensional inputs only. This chapter implements a three-dimensional convolutional neural networks (CNN) model for video classification to analyse the classification accuracy gained using the 3D CNN model. The 3D convolutional networks are preferred for video classification since they inherently apply convolutions in the 3D space.