Despite the growing volume of time series data across various domains, detecting anomalies remains challenging due to the complexity and dynamic nature of the data. Traditional monitoring systems are inefficient in capturing contextual and temporal anomalies that are only viable through time and handling high-dimensional data. From implementation to deployment, this paper presents an anomaly detection system on a cyber-physical system by integrating Variational Autoencoders (VAE) with Long Short-Term Memory (LSTM) networks and One-Class Support Vector Machine (OCSVM), forming a hybrid VAE-LSTM-OCSVM model. The proposed architecture positions itself as a zero-day anomaly detector, by learning the nominal functioning of systems, enabling it to identify deviations from normal operations without prior knowledge of specific anomalies. This capability significantly enhances the model's utility in online monitoring, making it adept at detecting unforeseen operational disruptions. We propose an Adaptive Loss Weight Adjustment Algorithm (ALWAA) to account for Domain incremental learning in our system, as required by the ISO/IEC 42001:2023 and ISO/IEC 23053:2022 standards. The model is evaluated on a dataset including 2 types of anomalies, comparing and demonstrating its superiority over existing methods. The findings suggest that the hybrid VAE-LSTM-OCSVM model offers a promising direction for more effective and efficient anomaly detection in time series data, with its ability to safeguard against known and unknown anomalies.

The integration of digital equipment and diverse automation platforms in modern power plants, including Nuclear Power Plants is due to the gradually increasing use of digital technologies. This development has raised new vulnerabilities that may endanger the critical systems for nuclear safety and physical protection at the facilities. An Instrumentation and Control system may comprise a huge number of systems, each of which must be accessed by several users. The performance of authentication and authorization processes of these users presents a challenge to the Instrumentation and Control system. Furthermore, legacy nuclear facilities may lack robust security controls such as authentication, authorization, and encryption services in their digital systems. Inadequate authentication creates vulnerabilities in Instrumentation and Control system protocols, network packets, products, and databases. Based on the authentication determination, a system may or may not permit authorized users accessing their resources. Authorization is the process of defining who and what should be permissible to have access to a specific resource. On the other hand, access control is the mechanism used to enforce authorization. In this paper, we will give an overview of current authentication and authorization schemes used in critical systems, analyze their vulnerabilities and give proper recommendations to be used. We envision that the findings in this paper provide a significant understanding of the threat of inappropriate authentication and access control mechanisms facing digital systems in Nuclear Power Plants with security and technical requirements to be used with.

The CS (Compressive Sensing) theory has been widely implemented in many areas, the CSI (Compressive Sensing Imaging) method is one of them. In this paper, in order to design the authenticated CSI system, we have introduced the CSI method and the image authentication mechanisms. The design strategies would be also discussed. Then, the CS based MAC (CSMAC) has been implemented in the CSI system, which makes the authentication and the sensing processes in one step. Furthermore, in order to adapt the CSI system's property, the CSMAC is designed to tolerate the content-preserving manipulations but oppose the harmful ones, so that the information integrity is protected with the content robustness.

A watermarking scheme for content based image authentication is proposed which, in addition to authentication, has the ability to localize and correct modifications / errors. The watermark is based on the frequency domain features of an image and it is protected using error correcting codes. The use of error correcting codes helps in error localization and correction. The frequency domain features are additionally protected using an approximate message authentication code. This provides tolerance in image authentication when some of the image data cannot be reconstructed due to transmission errors or by legitimate image processing operations such as quantization, compression etc. The minor variations in the image data might not change the content of the image and therefore by correcting some errors, and being tolerant to the errors below a pre defined threshold, results in successful content authentication. Simulation results support that some unintentional data modifications, such as those due to minor channel noise, can be localized and corrected resulting in successful content authentication. Additionally, the simulation results for intentional modifications show the error localization and forgery detection capability of the proposed algorithm.

A novel two-phase robust content-based image authentication scheme is introduced. The proposed scheme is constructed based on a combination of hard and soft authentication using two existing generic approximate message authentication codes (AMACs). The AMACs combine error- correcting codes with cryptographic primitives such as message authentication codes and symmetric encryption algorithms. The message authentication codes are used for hard authentication, whereas the error-correcting codes introduce a certain degree of robustness in authentication. This is achieved by correcting minor unintentional modifications as a result of common image processing operations such as quantization , compression , and noise addition. The two-phase image authentication scheme verifies the authenticity of an image in two phases. The low frequency elements of the image in a transform domain are subjected to the first phase while some higher frequency elements are left to the second phase if the first phase succeeds. The proposed scheme tolerates common content- preserving modifications in an image but can discriminate intentional modifications affecting the image content. Mathematical bounds for the accuracy and the security level of the proposed approach are estimated and the performance is compared with some other well-known schemes in the literature. The results demonstrate that the proposed scheme shows high discriminating capability and can detect different types of meaningful forgery attacks on images while preserving the robustness. It also outperforms the benchmark image authentication schemes in terms of tradeoff between robustness and fragility.

Although the perceptual image hashing is one of the promising techniques for image authentication, most existing methods cannot well distinguish content changing manipulations from acceptable content preserving modifications, especially when the size of the manipulated area is relatively small. In this regard, a new image hash algorithm is proposed to enhance the tamper detection capability by employing one of the most well-known local feature descriptors, Histogram of Oriented Gradients (HOG), for the feature extraction method. In this paper, image intensity transform using a random number generator, HOG feature computation, Successive Mean Quantization Transform (SMQT), and bit-level permutation are utilized to obtain a secure and robust hash value. Additionally, the performance of the proposed method is measured, and compared with existing algorithms by the Receiver Operating Characteristics (ROC) analysis.

Perceptual image hashing has received an increase dattention as one of the most important components for content based image authentication in recent years. Content based image authentication using perceptual image hashing is mainly classified into four different categories according to the feature extraction scheme. However, all the recently published literature that belongs to the individual category has its own strengths and weaknesses related to the feature extraction scheme. In this regard, this paper proposes a hybrid approach to improve the performance by combining two different categories: low-level image representation and coarse image representation. The proposed method employs a well-known local feature descriptor, the so-called Histogram of Oriented Gradients (HOG), as the feature extraction scheme in conjunction with Image Intensity Random Transformation (IIRT), Successive Mean Quantization Transform (SMQT), and bit-level permutation to construct a secure and robust hash value. To enhance the proposed method, a Key Derivation Function (KDF) and Error Correction Code (ECC) are applied to generate a stable subkey based on the coarse image representation. The derived subkey is utilized as a random seed in IIRT and HOG feature computation. Additionally, the experimental results are presented and compared with two existing algorithms in terms of robustness, discriminability, and security.

Wireless Multimedia Sensor Networks (WMSNs) are commonly used for communicating sensitive data which help in many important decision makings, so that it is crucial to ensure the received data are not manipulated in transit and originated from the correct source. In the security perspective, however, the characteristics of WMSNs and the nature of multimedia make data authentication schemes more complex, especially for data integrity. In this regard, the aim of this paper is to investigate the feasibility of content-based authentication using image hashing technique as an alternative data authentication scheme in WMSNs. To assess the feasibility, the general requirements for image authentication in WMSNs are discussed in this paper. Additionally, the performance of five selected image hashing algorithms is measured with respect to robustness, sensitivity, and security. By comparing and analyzing the performance of the selected algorithms, this paper provides a perspective on the potential feasibility and limitations as an alternative to the traditional authentication scheme in WMSNs.

Abstract If the results of the latest studies for Internet usage are to be believed, worldwide 12 million TV consumers will be using Internet protocol TV (IPTV) instead of the traditional TV broadcasting by the year 2010. These figures were published by ABI Research in 2006. Furthermore, analysts of Informa Telecoms & Media are forecasting the worldwide grow in revenue of IPTV to be 10 billion dollar by 2010. The revolution that is described by these figures implies on the one hand an enormous increase in sales values but on the other hand causes problems in handling the data volume. Moreover, IPTV will be attracting criminal attacks like Pay‐TV has in traditional broadcasting. Therefore, not only efficient encoding of media data has to be applied to save transmission capacity but also security mechanisms should be established to prevent unauthorised access. This paper will give a short overview of possible infrastructure setup as well as a method for the use of time‐limited keys. Copyright © 2008 John Wiley & Sons, Ltd.