Cloud computing has revolutionized the world, opening up new horizons with bright potential due to its performance, accessibility, low cost, and many other benefits. Cloud computing is the on-demand availability of computer system resources, especially data storage (cloud storage) and computational power. Cloud computing refers to data centers accessible to numerous customers over the Internet. It has the ability to utilize computing resources at a low cost and fast speed. Cloud data security is becoming increasingly important as we shift our devices, data centers, business processes, and other assets to the cloud. Comprehensive security policies, corporate security culture, and cloud security solutions are used to ensure the level of cloud data security. Many techniques exist to protect data communication in the cloud environment, including encryption, which is the primary component of data security and the mechanism by which data or message transmission confidentiality and integrity are achieved. Current researchers have focused on genetics-based cryptography; genetics has been implemented in cryptography for data computation, storage, and transmission. This survey paper analyzes the new type of cryptographic approaches based on genetic science to generate robust sub-keys and robust cryptographic techniques based on homologous genetics (DNA, RNA, and mRNA) to improve security in the cloud. This work reviews several approaches based on genetic cryptography and their applications and drawbacks. In addition, the paper introduces the architecture of cloud computing along with the fundamental challenges of cloud computing applications.

Federated learning (FL) is a promising collaborative and privacy-preserving machine learning approach in data-rich smart cities. Nevertheless, the inherent heterogeneity of these urban environments presents a significant challenge in selecting trustworthy clients for collaborative model training. The usage of traditional approaches, such as the random client selection technique, poses several threats to the system’s integrity due to the possibility of malicious client selection. Primarily, the existing literature focuses on assessing the trustworthiness of clients, neglecting the crucial aspect of trust in federated servers. To bridge this gap, in this work, we propose a novel framework that addresses the mutual trustworthiness in FL by considering the trust needs of both the client and the server. Our approach entails: 1) creating preference functions for servers and clients, allowing them to rank each other based on trust scores; 2) establishing a reputation-based recommendation system leveraging multiple clients to assess newly connected servers; 3) assigning credibility scores to recommending devices for better server trustworthiness measurement; 4) developing a trust assessment mechanism for smart devices using a statistical interquartile range (IQR) method; and 5) designing intelligent matching algorithms considering the preferences of both parties. Based on simulation and experimental results, our approach outperforms baseline methods by increasing trust levels, global model accuracy, and reducing nontrustworthy clients in the system.

Federated Learning (FL) is a revolutionary privacy-preserving distributed learning framework that allows a small group of users to cooperatively build a machine-learning model using their own data locally. Smart cities are areas that can generate high volume and critical data, which has the potential to revolutionize federated learning. Nevertheless, it is highly challenging to select a trustworthy group of clients to collaborate in model training. The utilization of a random selection technique would pose many threats due to malicious clients’ targeted and untargeted attacks. Such vulnerability may cause attacks and poisoning in the produced model. To address this problem, we present a mutual trust client-server selection approach based on matching game theory and bootstrapping mechanisms for federated learning in smart cities. Our solution entails the creation of: (1) preference functions for federated servers and smart devices (i.e., IoT/IoV) that enables them to sort each other based on trust score, (2) light feedback-base technique that leverages the cooperation of multiple client devices to assign trust value to the newly connected federated server, and (3) intelligent matching algorithms consider trust preferences of both parties in their design. According to our simulation results, our technique outperforms the baseline selection approach VanillaFL in terms of increasing the trust level and hence the global accuracy of the federated learning model and optimizing the number of untrusted selected clients.

Summary Cloud computing (CC) refers to the on‐demand availability of network resources, particularly data storage and processing power, without requiring special or direct administration by users. CC, which just made its debut as a collection of public and private data centers, provides clients with a unified platform throughout the Internet. Cloud computing has revolutionized the world, opening up new horizons with bright potential due to its performance, accessibility, low cost, and many other benefits. Due to the exponential rise of cloud computing, systems based on cloud computing now require an effective data security mechanism. Comprehensive security policies, corporate security culture, and cloud security solutions are used to ensure the level of cloud data security. Many techniques exist to protect data communication in the cloud environment, including encryption. Encryption algorithms play an important role in information security systems and various cloud computing‐based systems. Current researchers have focused on lightweight cryptography, genetics‐based cryptography, and machine learning (ML) algorithms for security in CC. This review study analyses CC security threats, problems, and solutions that use one or more algorithms. The work discusses several lightweight cryptographies, genetics‐based cryptography and different ML algorithms that are used to overcome cloud security issues, including supervised, unsupervised, semi‐supervised, and reinforcement learning. Moreover, we enlist future research directions to secure CC models.

Automatic Dependent Surveillance Broadcast (ADS-B) centrally contributes to aircraft traffic control in the US and Europe since 2020. ADS-B messages contain information about aircraft location and tracks to provide better real-time traceability of aircraft in space. However, the lack of security mechanisms will be an obstacle for trusting the ADS-B technology. Thus, countermeasures should be integrated to secure the communication and evaluate the integrity and trustworthiness of received messages. In this paper, we design a message verification protocol called MAVPro to evaluate the trustworthiness of received ADS-B messages whose authenticity and integrity could otherwise not be verified. The main idea behind MAVPro is to compare location claims in received ADS-B messages with expected aircraft locations, which are computed using predicted trajectory information (e. g., velocity, elapsed time, aircraft acceleration, heading information) and a set of pre-trusted, continuously updated anchors. Our protocol is able to evaluate the trustworthiness of received messages if as little as one ADS-B receiver obtains a message --- as opposed to four receivers required for using multilateration-based techniques to verify position claims. Thus we are able to considerably extend the coverage area where security checks can be applied compared to existing solutions. We evaluate MAVPro based on real-time data from the OpenSky network, analyze its performance, and verify its applicability to address ADS-B security concerns. MAVPro is backwards compatible and does not require changes to the ADS-B infrastructure.