Panoramic and periapical radiograph tools help dentists in diagnosing the most common dental diseases, such as dental caries. Generally, dental caries is manually diagnosed by dentists based on panoramic and periapical images. For several reasons, such as carelessness caused by heavy workload and inexperience, manual diagnosis may cause unnoticeable dental caries. Thus, computer-based intelligent vision systems supported by machine learning and image processing techniques are needed to prevent these negativities. This study proposed a novel approach for the automatic diagnosis of dental caries based on periapical images. The proposed procedure used a multi-input deep convolutional neural network ensemble (MI-DCNNE) model. Specifically, a score-based ensemble scheme was employed to increase the achievement of the proposed MI-DCNNE method. The inputs to the proposed approach were both raw periapical images and an enhanced form of it. The score fusion was carried out in the Softmax layer of the proposed multi-input CNN architecture. In the experimental works, a periapical image dataset (340 images) covering both caries and non-caries images were used for the performance evaluation of the proposed method. According to the results, it was seen that the proposed model is quite successful in the diagnosis of dental caries. The reported accuracy score is 99.13%. This result shows that the proposed MI-DCNNE model can effectively contribute to the classification of dental caries.

The security of resource-constrained devices is critical in the IoT field, given that everything is interconnected. Therefore, the National Institute of Standards and Technology (NIST) initialized the lightweight cryptography (LWC) project to standardize the lightweight cryptography algorithms for resource-constrained devices. After two rounds, the NIST announced the finalists in 2021. The finalist algorithms are Ascon, Elephant, GIFT-COFB, Grain-128AEAD, ISAP, PHOTON-Beetle, Romulus, SPARKLE, TinyJambu, and Xoodyak. The final round of the competition is still in progress, and the NIST will select the winner based on their and third-party evaluations. In this paper, we review the 10 finalists mentioned above, discuss their constructions, and classify them according to the underlying primitives. In particular, we analyze these ciphers from different perspectives, such as cipher specifications and structures, design primitives, security parameters, advantages and disadvantages, and existing cryptanalyses. We also review existing analyses of these finalists with a specific focus on the review of fault attacks. We hope the study compiled in this paper will benefit the cryptographic community by providing an easy-to-grasp overview of the NIST LWC finalists.

Cybersecurity has become one of the focuses of organisations. The number of cyberattacks keeps increasing as Internet usage continues to grow. As new types of cyberattacks continue to emerge, researchers focus on developing machine learning (ML)-based intrusion detection systems (IDS) to detect zero-day attacks. They usually remove some or all attack samples from the training dataset and only include them in the testing dataset when evaluating the performance. This method may detect unknown attacks; however, it does not reflect the long-term performance of the IDS as it only shows the changes in the type of attacks. In this work, we focused on evaluating the long-term performance of ML-based IDS. To achieve this goal, we proposed evaluating the ML-based IDS using a dataset created later than the training dataset. The proposed method can better assess the long-term performance as the testing dataset reflects the changes in the attack type and network infrastructure changes over time. We have implemented six of the most popular ML models, including decision tree (DT), random forest (RF), support vector machine (SVM), naïve Bayes (NB), artificial neural network (ANN), and deep neural network (DNN). These models are trained and tested with a pair of datasets with symmetrical classes. Our experiments using the CIC-IDS2017 and the CSE-CIC-IDS2018 datasets show that SVM and ANN are most resistant to overfitting. Our experiments also indicate that DT and RF suffer the most from overfitting, although they perform well on the training dataset. On the other hand, our experiments using the LUFlow dataset have shown that all models can perform well when the difference between the training and testing datasets is small.

Ensuring the cloud data security is a major concern for corporate cloud subscribers and in some cases for the private cloud users. Confidentiality of the stored data can be managed by encrypting the data at the client side before outsourcing it to the remote cloud storage server. However, once the data is encrypted, it will limit server’s capability for keyword search since the data is encrypted and server simply cannot make a plaintext keyword search on encrypted data. But again we need the keyword search functionality for efficient retrieval of data. To maintain user’s data confidentiality, the keyword search functionality should be able to perform over encrypted cloud data and additionally it should not leak any information about the searched keyword or the retrieved document. This is known as privacy preserving keyword search. This paper aims to study privacy preserving keyword search over encrypted cloud data. Also, we present our implementation of a privacy preserving data storage and retrieval system in cloud computing. For our implementation, we have chosen one of the symmetric key primitives due to its efficiency in mobile environments. The implemented scheme enables a user to store data securely in the cloud by encrypting it before outsourcing and also provides user capability to search over the encrypted data without revealing any information about the data or the query.

The lack of data outsourcing in healthcare management systems slows down the intercommunication and information sharing between different entities. A standard solution is outsourcing the electronic health record (EHR) to a cloud service provider (CSP). The outsourcing of the EHR should be performed securely without compromising the CSP functionalities. Searchable encryption would be a viable approach to ensure the confidentiality of the data without compromising searchability and accessibility. However, most existing searchable encryption solutions use centralised architecture. These systems have trust issues as not all the CSPs are fully trusted or honest. To address these problems, we explore blockchain technology with smart contract applications to construct a decentralised system with auditable yet immutable data storage and access. First, we propose a blockchain-based searchable encryption scheme for EHR storage and updates in a decentralised fashion. The proposed scheme supports confidentiality of the outsourced EHR, keyword search functionalities, verifiability of the user and the server, storage immutability, and dynamic updates of EHRs. Next, we implement a prototype using JavaScript and Solidity on the Ethereum platform to demonstrate the practicality of the proposed solution. Finally, we compare the performance and security of the proposed scheme against existing solutions. The result indicates that the proposed scheme is practical while providing the desired security features and functional requirements.