Smoke detection is essential for safety and fire protection systems, and incorporating machine learning (ML) algorithms significantly improves its precision and effectiveness. The ML techniques for binary classification are investigated and assessed in this work by utilizing different algorithms such as: Logistic Regression (LR), Naïve Bayes (NB), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RT), and Support Vector Machine (SVM). The smoke detection dataset chosen for this study contains around 62,630 with 14 features instances where 44,757 instances have been identified as fire, whereas 17,873 instances have been classed as no fire. Moreover, these cases are determined to be unbalanced. The data pre-processing techniques utilized for training and performance evaluation are SMOTE-Tomek, the removal of unnecessary features, and the correlation matrix for dimensionality feature selection. The efficacy of the fire and smoke detection model is then compared with the following metrics such as: computational time, accuracy, precision, recall, and F1-score.

Due to technological advancements, social media usage has increased a lot resulting in a huge spread of fake information and false news among users of different languages. To reduce the spread of fake information, there is a need to detect the fake/false information being posted on social media apps like Twitter, Facebook, Instagram, and many. In order to identify false news, researchers employ models based on machine learning, natural language processing, and deep learning. These models are to be trained initially by huge amounts of data so that the models can gain knowledge from the trained data and predict the output for the new data provided. This study performs a detailed systematic review on different recent federated learning models being proposed for detecting fake news. It provides a detailed comparison of recently published articles related to fake-news detection using federated learning in terms of models they used. This study also provides different datasets which can be used in detecting fake-news using federated learning.

Network security is essential in the linked world of today because critical information systems are the target of an increasing number of malicious attacks and cyberthreats. Intrusion detection systems, or IDS, are primarily responsible for protecting networks against these types of attacks. Through the examination of network traffic characteristics, machine learning algorithms have developed into useful instruments for enhancing intrusion detection systems’ capabilities. In this paper, we provide a comparison of several machine learning techniques for network intrusion detection. We investigate Decision Trees, K-Nearest Neighbors, AdaBoost, Gaussian Naive Bayes, Random Forest, Logistic Regression, and Gradient Boosting in identifying and categorizing network intrusions. For this study, we employ a publicly available network traffic dataset. We evaluate the effectiveness of each technique through multiple experiments, measuring its computational efficiency, accuracy, precision, recall, and F1 score. Our study illustrates the benefits and drawbacks of these algorithms as well as their suitability for use in different intrusion detection scenarios. This study also highlights the significance of selecting appropriate machine learning algorithms that are tailored to the properties of network traffic data to increase the resilience of network security infrastructures.

Cloud-based storage service has emerged as a promising alternative to managing local storage, offering users additional features, such as storage, backup, and restoration of various resources, including software, applications, and sensitive private information, within a virtual database, while ensuring data confidentiality and security. However, the widespread use of cloud services by individuals and organisations raises concerns regarding user accessibility and data security due to increasing social threats and adversarial attacks. Searchable encryption (SE) has been introduced to address these issues, providing a secure environment for a convenient and effective way of data searching and sharing. SE models have been advanced by integrating blockchain functionalities to tackle certain existing vulnerabilities and enhance user accessibility, data privacy, and integrity. This survey work explores various research works on SE techniques leveraging cloud and blockchain functionalities, discussing and categorizing the diverse approaches based on different criteria. This study also discusses the different enhancements made to SE techniques over the years, including the underlying requirements that led to the inclusion of blockchain functionalities. Moreover, this study provides a comparative analysis of existing survey works done in this area, which highlights a lack of recent literature surveys that thoroughly explore blockchain-based public key encryption with keyword search (PEKS) schemes. Particularly, we delve into the technical aspects of PEKS by classifying, analyzing and comparing different functionalities based on various aspects. The survey concludes with a comparative analysis of existing PEKS solutions and a discussion on identified research gaps, aiming to improve future research on PEKS approaches in this emerging field.

Edge–cloud coordination offers the chance to mitigate the enormous storage and processing load brought on by a massive increase in traffic at the network's edge. Though this paradigm has benefits on a large scale, outsourcing the sensitive data from the smart devices deployed in an Internet of Things (IoT) application may lead to privacy leakage. With an attribute-based keyword search (ABKS), the search over ciphertext can be achieved; this reduces the risk of sensitive data explosion. However, ABKS has several issues, like huge computational overhead to perform multi-keyword searches and tracing malicious users. To address these issues and enhance the performance of ABKS, we propose a novel traceable and lightweight attribute-based keyword search technique in an Edge–cloud-assisted IoT, named TL-ABKS, using edge–cloud coordination. With TL-ABKS, it is possible to do effective multi-keyword searches and implement fine-grained access control. Further, TL-ABKS outsources the encryption and decryption computation to edge nodes to enable its usage to resource-limited IoT smart devices. In addition, TL-ABKS achieves tracing user identity who misuse their secret keys. TL-ABKS is secure against modified secret keys, chosen plaintext, and chosen keyword attacks. By comparing the proposed TL-ABKS with the current state-of-the-art schemes, and conducting a theoretical and experimental evaluation of its performance and credibility, TL-ABKS is efficient.

Attribute-based keyword search (ABKS) achieved significant attention for data privacy and fine-grained access control of outsourced cloud data. However, most of the existing ABKS schemes are designed based on a semi-honest and curious cloud storage system in which the search fairness between two parties becomes questionable. Hence, it is vital to building a protocol that provides mutual trust between the cloud and its users. This paper proposes a blockchain-aided keyword search over encrypted data, which achieves search fairness between the cloud and its users using Ethereum blockchain and smart contracts. Additionally, the system accomplishes fine-grained access control, limiting access to the data to only those who have been given permission. Besides, the scheme allows multi keyword search by the users. The security analysis shows that our scheme is indistinguishable against chosen-plaintext attack and other malicious attacks. The performance analysis shows that the scheme is efficient.

Cloud storage is one of the cloud computing services which allows data users to store their data remotely to the cloud. Thus, most individuals, institutions, and organizations are outsourcing their data to the cloud. Most popular cloud-based storage services are Amazon S3, Google Drive, Microsoft Azure, Apple iCloud, Dropbox, etc. Cloud storage service brings significant benefits to data owners, say, (1) reducing capital and management costs (2) reducing cloud users’ burden of storage management and equipment maintenance, (3) avoiding investing a large amount of hardware, (4) accessing data over the Internet from any location from any devices such as desktop computers, laptops, tablets, and smartphones which offers increased flexibility and accessibility.

Attribute-based searchable encryption (ABSE) allows only authorized users to perform a keyword search over encrypted data in the cloud while preserving the data privacy and keyword privacy. Although ABSE provides data privacy, access control, and keyword search, it does not support data authenticity which plays a major role in the cloud environment to ensure that the data is not modified. Alongside, improving search efficiency in ABSE becomes mandatory since the cloud is attracting massive data. To address these issues, in this paper, we propose a practical verifiable multi-keyword attribute-based searchable signcryption scheme in cloud storage. The scheme uses ciphertext-policy attribute-based signcryption to achieve data privacy, access control, and data authenticity. Further, we integrate the multi-dimensional B+-tree with the Merkle tree in index construction to enhance the search efficiency and to verify the search results. The security analysis proves that our scheme satisfies security requirements such as data privacy and authenticity, index and query privacy, trapdoor unlinkability. We also prove that our scheme is secure against chosen plaintext attacks and signature forgery attacks. Finally, the performance analysis demonstrates that the proposed scheme is efficient and practical.

Attribute-based keyword search (ABKS) achieves privacy-preserving keyword search and fine-grained access control over encrypted data in the cloud. However, existing ABKS schemes cannot be directly applied for resource-constrained (such as Internet of Things) devices due to heavy computation overhead. In addition, identifying the malicious user who misuses the secret key is difficult if more than one user is having the same set of attributes. Furthermore, user revocation and attribute revocation are two important challenges in real-world applications. To address these challenges, this article proposes a FELT-ABKS: fog-enabled lightweight traceable ABKS over encrypted data by using ciphertext-policy ABKS to realize keyword search and fine-grained access control. FELT-ABKS achieves minimal computation cost at end users by transferring maximum computation to fog nodes. Furthermore, FELT-ABKS traces the malicious users who misuse their secret key. Besides, it supports user revocation and attribute revocation. The security analysis proves that FELT-ABKS is secure against the chosen keyword attack, chosen-plaintext attack, and modify secret key attack. Finally, experiments demonstrate that FELT-ABKS is lightweight and feasible.

Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) provides data privacy and achieves fine-grained access control over encrypted data in the cloud. However, authorized users may misuse the secret key for financial benefits in a multi-user scenario. Thus, tracing those malicious users and revoking them from the system is essential. Alongside this, most existing schemes have only a single authority to generate the secret key, which may lead to misuse of the secret key. To address these problems, this paper proposes a traceable and revocable multi-authority attribute-based keyword search in the cloud. The scheme involves two authorities generating the user secret key to restrict any individual authority's unauthorized access to cloud data. The scheme also traces malicious users and revokes them from the system. Further, we prove that the scheme is secure against chosen keyword attacks, chosen plaintext attacks, and traceability. And also verify the security against malicious authorities. The performance analysis shows that the proposed scheme is efficient in computation cost compared to the state-of-the-art schemes.

Ciphertext-policy attribute-based searchable encryption (CP-ABSE) is widely used in the cloud environment to provide data privacy and fine-grained access control over encrypted data. The existing CP-ABSE schemes are designed based on bilinear pairing hardness assumptions to prove their security. However, these schemes are vulnerable to quantum attacks, i.e., adversaries can break the security of these schemes with the use of quantum computers. To address this issue, in this paper, we propose a novel ciphertext-policy attribute-based searchable encryption from lattice (CP-ABSEL) in cloud storage, since lattice-based cryptography is quantum attacks free. In CP-ABSEL, we adopted learning with errors (LWE) hardness assumption to resist from quantum attacks. Further, CP-ABSEL is indistinguishable against the chosen keyword attack and indistinguishable against chosen plaintext attack. Moreover, CP-ABSEL allows only legitimate users to perform a keyword search over an encrypted index, and unauthorized users cannot get even the ciphertext form of documents. The performance analysis proves that CP-ABSEL is efficient and practical.

With the emergence of cloud computing, data owners are showing interest to outsource the data to the cloud servers and allowing the data users to access the data as and when required.However, outsourcing sensitive data into the cloud leads to privacy issues. Encrypting the data before outsourcing provides privacy, but it does not provide search functionality. To achieve search over encrypted data without compromising the privacy, searchable encryption (SE) schemes have been proposed. It protects the user’s sensitive information by providing searchability on encrypted data stored in the cloud. In this paper, we surveyed different SE schemes which are existed in the cloud domain. In this survey, we presented the taxonomy of the SE schemes: symmetric searchable encryption, public key searchable encryption, and attribute-based searchable encryption schemes, and then provided a detailed discussion on the SE schemes in terms of index structure and search functionality. A comparative analysis of SE schemes is also provided on security and performance. Furthermore, we discussed the challenges, future directions, and applications of SE schemes.

Attribute-based searchable encryption (ABSE) schemes provide searchability and fine-grained access control over encrypted data in the cloud. Although prior ABSE schemes are designed to provide data protection and retrieval efficiency, they are suffering from the following issues. 1) A key-escrow problem, which may lead to the misuse of the user's secret key. 2) A single keyword search, which may produce irrelevant search results and also vulnerable in real-world applications. 3) A static policy update mechanism, which incurs high computation and communication overheads. In this paper, we propose a novel ABSE scheme called a key-escrow free attribute-based multi-keyword search with dynamic policy updates in cloud computing (KAMS-PU) to addresses all the above-stated issues. The security analysis proves that KAMS-PU is secure against malicious authority attacks and chosen keyword attack (CKA) in the random oracle model. Furthermore, performance analysis proves that KAMS-PU is efficient and practical in real-world applications.