Search

It is difficult to manage massive amounts of data in an overlying environment with a single server. Therefore, it is necessary to comprehend the security provisions for erratic data in a dynamic environment. The authors are concerned about the security risk of vulnerable data in a Mobile Edge based distributive environment. As a result, edge computing appears to be an excellent perspective in which training can be done in an Edge-based environment. The combination of Edge computing and consensus approach of Blockchain in conjunction with machine learning techniques can further improve data security, mitigate the possibility of exposed data, and it reduces the risk of a data breach. As a result, the concept of federated learning provides a path for training the shared data. A dataset was collected that contained several vulnerable, exposed, recovered, and secured data and data security was precepted under the surveillance of two-factor authentication. This paper discusses the evolution of data and security flaws and their corresponding solutions in smart edge computing devices. The proposed model incorporates data security using consensus approach of Blockchain and machine learning techniques that include several classifiers and optimization techniques. Further, the authors applied the proposed algorithms in an edge computing environment by distributing several batches of data to different clients. As a result, the client privacy was maintained by using Blockchain servers. Furthermore, the authors segregated the client data into batches that were trained using the federated learning technique. The results obtained in this paper demonstrate the implementation of a Blockchain-based training model in an edge-based computing environment. [ABSTRACT FROM AUTHOR]

Cyber-Physical Systems (CPS) are integral components of modern, interconnected environments, playing a crucial role in various applications such as smart infrastructure and autonomous systems. These systems operate in complex and ever-evolving settings, where resilience is an essential characteristic. Recently, several Machine Learning (ML) techniques have been proposed to design and implement resilience in CPS. However, this approach has often prioritized performance gains and adaptability enhancements, leading to a disregard for the potential dangers linked to centralized data processing, including data breaches and privacy infringements. To harness the full potential of ML in CPS, this paper introduces a distributed intelligence framework that equally prioritizes security, data privacy, and adaptability. The proposed framework is implemented through the integration of Federated Machine Learning techniques, where the CPS architecture is decentralized, allowing data processing to occur locally on individual nodes or devices. This decentralized approach facilitates the aggregation of insights from multiple sources without the need for centralized data processing, thereby minimizing the risks associated with data breaches and privacy violations. We further validate the viability of the proposed framework through its successful implementation in a real-world industrial CPS application, specifically focused on fault prediction within industrial CPS environments. In addition to its privacy and security benefits, our approach also achieved promising results in terms of accuracy and precision. [ABSTRACT FROM AUTHOR]

With the vigorous development of cloud computing, most organizations have shifted their data and applications to the cloud environment for storage, computation, and sharing purposes. During storage and data sharing across the participating entities, a malicious agent may gain access to outsourced data from the cloud environment. A malicious agent is an entity that deliberately breaches the data. This information accessed might be misused or revealed to unauthorized parties. Therefore, data protection and prediction of malicious agents have become a demanding task that needs to be addressed appropriately. To deal with this crucial and challenging issue, this paper presents a Malicious Agent Identification-based Data Security (MAIDS) Model which utilizes XGBoost machine learning classification algorithm for securing data allocation and communication among different participating entities in the cloud system. The proposed model explores and computes intended multiple security parameters associated with online data communication or transactions. Correspondingly, a security-focused knowledge database is produced for developing the XGBoost Classifier-based Malicious Agent Prediction (XC-MAP) unit. Unlike the existing approaches, which only identify malicious agents after data leaks, MAIDS proactively identifies malicious agents by examining their eligibility for respective data access. In this way, the model provides a comprehensive solution to safeguard crucial data from both intentional and non-intentional breaches, by granting data to authorized agents only by evaluating the agent's behavior and predicting the malicious agent before granting data. The performance of the proposed model is thoroughly evaluated by accomplishing extensive experiments, and the results signify that the MAIDS model predicts the malicious agents with high accuracy, precision, recall, and F1-scores up to 95.55%, 95.30%, 95.50%, and 95.20%, respectively. This enormously enhances the system's security in terms of authorized data access accuracy up to 55.49%, precision up to 43.15%, recall up to 55.49%, and F1-score up to 39.96%, respectively, as compared to state-of-the-art work. [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

Data leakage is a problem that companies and organizations face every day around the world. Mainly the data leak caused by the internal threat posed by authorized personnel to manipulate confidential information. The main objective of this work is to survey the literature to detect the existing techniques to protect against data leakage and to identify the methods used to address the insider threat. For this, a literature review of scientific databases was carried out in the period from 2011 to 2022, which resulted in 42 relevant papers. It was obtained that from 2017 to date, 60% of the studies found are concentrated and that 90% come from conferences and publications in journals. Significant advances were detected in protection systems against data leakage with the incorporation of new techniques and technologies, such as machine learning, blockchain, and digital rights management policies. In 40% of the relevant studies, significant interest was shown in avoiding internal threats. The most used techniques in the analyzed DLP tools were encryption and machine learning. [ABSTRACT FROM AUTHOR]

Medical records are one of the crucial documents and a significant asset for anyone seeking treatment. Electronic health records (EHRs) have made a dynamic shift by making them easier to manage, facilitate and share among various stakeholders such as doctors, lab technicians, and insurance agents. EHRs are vulnerable to hacker, cybercriminal attacks, and data breaches. Once compromised, health records cannot be retrieved. As a result, patients must have control over who gets their EHRs, when they get them, and where they get them. To address the aforementioned issue, this paper proposes a blockchain-based secure record-keeping and trustworthy sharing system. In order to do this, a distributed off-chain storage architecture for large-scale medical data storage is developed, which overcomes the drawbacks of on-chain data storage and enhances scalability. The distributed storage, i.e., InterPlanetary File System, is a content-addressable storage that ensures the integrity of the content such that a slight modification in the stored EHR records results in a change in the obtained hash value. Furthermore, a Ciphertext Policy Attribute-Based Encryption (CP-ABE) algorithm integrated with blockchain technology is designed for fine-grained access control, allowing only authorized users to access specific EHR data based on their attributes. The combination of CP-ABE with blockchain technology provides a tamper-proof and verifiable audit trail of all data access and updations made to EHRs. This enhances accountability and ensures that the patients or owners can track and verify all actions taken on the data. To implement the proposed system, the Remix-Ethereum IDE is used. Smart contracts (SCs) are designed with access permissions so patients have complete control over their records. The scalability and immutability of the system is ensured by storing the hash of the encrypted EHRs on the blockchain and the actual encrypted records on IPFS. The security analysis of the proposed system is carried out by evaluating its resistance to various attacks. Additionally, potential security flaws in the proposed SCs are investigated using the Oyente tool. Different test cases are presented to demonstrate the functionality and cost analysis of the proposed system. [ABSTRACT FROM AUTHOR]

Multiple benefits (submitting healthcare bills to one or more organizations) and data breaches (tampering of healthcare data by healthcare organization authorities) are typical frauds happening due to the centralization of authority in healthcare systems. Preventing multiple benefits and data breaches can greatly lessen the huge losses to healthcare systems. In this paper, we propose an extended lightweight blockchain (ELB) based collaborative healthcare system for decentralizing the authority in healthcare organizations. The proposed architecture is rigorously tested in avoiding multiple benefits and data breaches and compared with the state-of-the-art methods. The experimental results evidenced that the proposed ELB architecture can effectively avoid multiple benefits and data breaches with less computation and communication overheads. [ABSTRACT FROM AUTHOR]

It is essential to ensure the data security of data analytical frameworks as any security vulnerability existing in the system can lead to a data loss or data breach. This vulnerability may occur due to attacks from live attackers as well as automated bots. However inside attacks are also becoming more frequent because of incorrectly implemented security requirements and access control policies. Thus, it is important to understand security goals and formulate security requirements and access control policies accordingly. Therefore, it is equally important to identify the existing security vulnerabilities of a given software system. To find the available vulnerabilities against any system, it is mandatory to conduct vulnerability assessments as scheduled tasks in a regular manner. Thus, an easily deployable, easily maintainable, accurate vulnerability assessment testbed or a model is helpful as facilitated by Linux containers. Nowadays Linux containers (LXCs) which have operating system level virtualization, are very popular over virtual machines (VMs) which have hypervisor or kernel level virtualization in high performance computing (HPC) due to reasons, such as high portability, high performance, efficiency and high security (Chae et al in Clust Comput 22:1765-1775, 2019. 10.1007/s10586-017-1511-2). Hence, LXCs can make an efficient and scalable vulnerability assessment testbed or a model by using already developed analyzing tools such as OpenVas, Dagda, PortSpider, MongoAudit, NMap, Metasploit Framework, Nessus, OWASP Zed Attack Proxy, and OpenSCAP, to assure the required security level of a given system very easily. To verify the overall security of any given software system, this paper first introduces a virtual, portable and easily deployable vulnerability assessment general testbed within the Linux container network. Next, the paper presents, how to conduct experiments using this testbed on a MongoDB database implemented in Singularity Linux containers to find the available vulnerabilities in 1. MongoDB application itself, 2. Images accompanied by containers, 3. Host, and 4. Network by integrating seven tools: OpenVas, Dagda, PortSpider, MongoAudit, NMap, Metasploit Framework, and Nessus to the container-based testbed. Finally, it discusses how to use generated results to improve the security level of the given system. [ABSTRACT FROM AUTHOR]

Cloud Computing is referred to as a set of hardware and software that are being combined to deliver various services of computing. The cloud keeps the services for delivery of software, infrastructure, and platform over the Internet based on the user's demand. In the IT industry, cloud computing plays an important role to access services anywhere in the world. With increasing demand and popularity of cloud computing, several types of threats and vulnerabilities are also increased. Data integrity and privacy are the key issues in cloud computing and are thoughtful as the data is stored in different geographical locations. Therefore, data integrity and privacy protection provisions are the most prominent factors of user's concerns about the cloud computing environment. In this paper, a new model based on a genetic algorithm (GA) CryptoGA is proposed to cope with data integrity and privacy issues. GA is used to generate keys for encryption and decryption which are integrated with a cryptographic algorithm to ensure privacy and integrity of cloud data. Known and common parameters i.e. execution time, throughput, key size, and avalanche effect are considered for evaluation and comparison. Ten different datasets are used in experiments for testing and validation. Experimental results analysis show that the proposed model ensures the integrity and preserves the privacy of the user's data against unauthorized parties. Moreover, the CryptoGA is robust and provides better performance on selected parameters as compared to state-of-the-art cryptographic algorithms i.e. DES, 3DES, RSA, Blowfish, and AES. [ABSTRACT FROM AUTHOR]

With the emergence of cloud computing paradigm in many scientific applications, outsourcing of computation has attracted a great amount of attention from the research community. Outsourcing of heavy computations such as multiplication of two large matrices has raised some security concerns. Data and the result of computation should be protected not only from attackers, but also from the cloud servers. Moreover, data owner should be able to verify the correctness of computation with complexity less than the original computation. The previous schemes either have expensive offline phase or do not support public verifiability. In this paper, first we find a security vulnerability in the Zhang-Lei's scheme for outsourcing of matrix multiplication where the cloud server can forge the result and pass the verification phase. Then, we present a secure and efficient publicly verifiable outsourcing of matrix multiplication scheme which achieves privacy protection of outsourced data and result, unforgeability of result, public verifiability and high efficiency. Our analyses show that compared with the related work, the proposed scheme is superior in terms of functionality, computation, communication and storage overhead, especially in verification computation overhead. [ABSTRACT FROM AUTHOR]

To provide a more reliable security for the network privacy, the access control protocol Priccess design of network privacy protection was studied. First of all, this paper presented the problems in wireless network security, and points out the key technologies, including privacy protection, user authentication, trust management, network security communication architecture and other technologies. Then, it made a brief analysis of the composition of the Priccess protocol, a wireless communication network in the roaming authentication scheme and wireless sensor network privacy data protection scheme. Furthermore, the roaming authentication scheme and wireless sensor networks data privacy protection in a wireless communication network was established. Finally, the results of the evaluation of the message load of Priccess protocol proved it was efficient for most of the user access devices, which could provide more efficient protection for the privacy of the network communication. [ABSTRACT FROM AUTHOR]

As one of the basic research methods of bioinformatics, DNA motif finding is of great significance to the study of mechanisms for regulating gene expression and the discovery of biological functional sites. However, because of the high sensitivity of DNA data, the privacy disclosure of these data during motif finding has become a bottleneck in the field of gene research. Meanwhile, traditional privacy protection data mining methods cannot deal with DNA sequences directly, and the existing private motif finding methods usually decrease the utility of the results. To solve these problems, we propose a high-utility motif finding algorithm based on ϵ -differential privacy, which is known as a rigorous definition of privacy with meaningful privacy guarantees in the presence of arbitrary external information. Our solution makes use of the closed frequent pattern set to reduce redundant motifs of result sets and obtain accurate motifs results, satisfying ϵ -differential privacy. Furthermore, a post-processing method based on the best linear unbiased estimate is used to optimize the utility of noisy consolidated motif support. Experiments on real-life DNA sequence datasets confirm that our algorithm is superior to the existing algorithms in terms of utility. [ABSTRACT FROM AUTHOR]

Despite more privacy preservation techniques available in wireless sensor networks (WSN), no modest technique dealt with compromised nodes. Among several applications, healthcare applications fit into WSNs environment for patient monitoring from work place, hospital and home. More predictable security threats are in healthcare applications against both outside and inside attacks. For example, data breach, access control, eavesdropping, modification, and impersonation are vulnerable. On hand clarifications protect the user's personal information from the external attackers. But, they are unable to fight against compromised attacks internally by knowing all user data and security credentials. The existing premier cryptosystem is unable to protect the user's data against compromised attacks. Also, WSNs provide flexible data aggregation structures and routing protocols to maintain end-to-end data privacy. In this proposal, a sensible approach is proposed to put off the inside attacks by many data servers to store user data. In this proposal, the paillier cryptosystem is used for distributing data to many data servers in a secured manner exclusively maintaining privacy. This proposal continues to preserve the data privacy only if any one of the data server is not compromised. A thorough security analysis and extensive simulations show that our protocol can ensure end-to-end privacy with low overhead for communication, memory and computation. [ABSTRACT FROM AUTHOR]