In recent years, traffic congestion have become a common problem in modern transportation systems, causing people to spend more time on the road, increased emissions, and elevated safety risks. Intelligent Transportation Systems (ITS) address these issues by integrating cutting-edge technologies, advanced sensing, innovative deep learning algorithms, and driver participation to enable real-time monitoring and predictive traffic management. However, the collection of sensitive driver spatiotemporal location data required for effective real-time analysis raises privacy concerns. Such detailed reporting can inadvertently expose individual travel patterns, daily routines, and personal habits, making drivers vulnerable to profiling, unauthorized surveillance, and even malicious exploitation. To address these challenges, this paper introduces a secure and privacy-preserving traffic forecasting framework that combines k-anonymity with functional encryption to guarantee protection of individual driver information while enabling accurate aggregation of encrypted reports. The aggregated data are then used to train a deep learning architecture that integrates Convolutional Long Short-Term Memory (Conv-LSTM) for spatial and short-term temporal dependencies with Bidirectional LSTM (Bi-LSTM) for capturing long-term periodic traffic patterns for forecasting. Extensive experiments on real-world datasets demonstrate that the proposed scheme achieves high forecasting accuracy, maintaining mean absolute error below 10% for a 60-minute forecasting horizon, while safeguarding driver privacy.

Load forecasting (LF) in smart grids is beneficial not only in mitigating equipment failures and power outages but also in facilitating effective power dispatching and infrastructure planning. To predict future loads accurately, the consumers' fine-grained energy consumption readings are fed into machine-learning (ML) models. However, revealing these readings enables adversaries to deduce confidential information about consumers, including details about their lifestyle, and hence their privacy is violated. To address this privacy issue, the existing works only focus on using federated learning (FL)-based approaches to train and obtain an accurate global LF model. Nevertheless, addressing the privacy violation problem during the LF process (in the deployment phase) after obtaining the global model for AMI networks has not been well investigated yet. Therefore, this paper proposes a novel, efficient, and decentralized approach that enhances the precision of LF while safeguarding the privacy of consumers. The proposed scheme incorporates inner product functional encryption (IPFE) to allow smart meters (SMs) to encrypt their readings with no need for a trusted key distribution center (KDC) while allowing LF without divulging or acquiring knowledge of the consumers' readings to protect their privacy. In addition, a hybrid deep learning approach is developed to construct an LF model that can yield precise forecasts. To show the feasibility of the proposed scheme, the performance of our scheme was assessed on a real energy consumption readings dataset, and the results demonstrate proficiency in LF while providing robustness and privacy preservation with reasonable communication efficiency.

In federated learning (FL) based electricity theft detection, detection nodes (DNs) locally train deep learning models on consumers' data and share only the local model parameters with an aggregation server (AS) to generate a global model shared by all nodes for better detection accuracy. However, several privacy concerns should be addressed including membership and inference attacks. To mitigate these attacks, several privacy-preserving aggregation schemes have been introduced. Nevertheless, existing FL detectors often overlook the threat of poisoning attacks, in which certain DNs hold maliciously labeled, i.e., poisoned, data during the training. This manipulated data can subsequently be exploited to introduce backdoors into the global model after its deployment. This paper introduces a novel approach that enhances privacy and resilience against poisoning attacks in FL-based electricity theft detection within smart grids. Our approach enables encrypting local parameters before sending them to the AS, thus safeguarding consumers' privacy. Additionally, it utilizes a cosine similarity test over encrypted data to detect and mitigate poisoning attacks by filtering out malicious local gradients from being considered in the global model computation. Through extensive evaluations, we demonstrate the effectiveness of our FL-based detector in substantially reducing the poisoning attack success rate even when 50% of DNs train their local models with malicious targeted power consumption data, all while preserving consumers' privacy.

Unmanned Aerial Vehicles (UAVs) are increasingly employed in cooperative surveillance missions where data collection across disparate areas is crucial. In such systems, data from all UAVs is collected and processed in a central server, making it vulnerable to breaches and unauthorized access. Federated Learning (FL) addresses these concerns by enabling collaborative model training without centralized data collection. In FL, each UAV trains a local model on its own data and only shares the model updates with a central server. The central server then aggregates these parameters to update a global model, which is redistributed to all participating UAVs. However, FL’s reliance on a central server introduces challenges, especially in geographically highly dynamic and dispersed scenarios. The central server can become a single point of failure and may struggle with the communication overhead and latency issues inherent in such dynamic environments. To overcome these limitations, this paper proposes a decentralized federated learning framework for multi-agent UAV systems. This approach facilitates direct sharing of local deep learning (DL) model parameters among UAVs, eliminating the need for a central server. Our approach employs the Metropolis-Hastings algorithm to ensure UAVs achieve consensus on shared model parameters, ensuring balanced weight distribution and stable training processes. We validate our fully distributed DL model aggregation using the ResNet-18 model. Our results confirm DFL’s effectiveness in achieving low RMSE values and rapid convergence, comparable to centralized FL, across dynamic UAV networks.

Electric Vehicles (EVs) are being widely adopted as a green alternative to fossil-based vehicles. However, the current charging infrastructure for EVs is inadequate to meet the growing charge demand. Vehicle-to-Vehicle (V2V) charging offers a promising solution that enables a charge supplier EV to provide charging services to a charge demander EV in a distributed manner. Nevertheless, V2V matching and charge scheduling can disclose sensitive location information about the drivers, such as their whereabouts and driving patterns. In this paper, we propose a privacy-preserving scheme for centralized optimal matching of demander EVs with supplier EVs, while protecting their sensitive information. In our scheme, charge demanders report to a matching server their encrypted location information and the requested energy quantities, whereas charge suppliers report encrypted charge costs such that the matching server can learn only the cost to match each demander to each supplier without revealing any location information or the exchanged charge amount. Then, the Hungarian algorithm is used to match demanders to suppliers while minimizing the total cost. The security analysis and simulation results show that our scheme can achieve optimal V2V matching while preserving drivers’ privacy with negligible computation overhead. Overall, our proposed scheme provides an effective solution for V2V charging, while maintaining privacy and confidentiality of sensitive drivers’ information.

The Internet of Things (IoT) has made it possible to gather patient data through a network of sensors, referred to as the wireless body area network (WBAN). However, the variability of the wireless channels can pose a challenge to the real-time functionality of Medical IoT (MIoT) systems. These delays can occur due to either natural or malicious congestion in the wireless channels. To address this issue, we present an efficient algorithm that partitions the WBAN nodes within an MIoT system to balance the traffic load across the entire system. In our model, each network partition includes an access point (AP) responsible for managing all the WBANs within its coverage range. Our proposed algorithm enables the APs to dynamically readjust their coverage range based on the overall traffic load, thereby evenly distributing the load among APs to alleviate congested areas. Moreover, the APs continuously monitor the traffic to detect and mitigate congested areas, regardless of whether the congestion is due to a natural load or a malicious traffic injection attack. Based on the simulations done using NS2, the proposed algorithm: 1) can resolve congestion of both cases very efficiently; 2) improves the network delay variation by at least 40%; and 3) improves the network energy consumption and network delay by at least 30% and 44%, respectively.

Ridesharing allows multiple persons to share one vehicle for their trips instead of using multiple vehicles. Ridesharing can reduce the number of vehicles in the street, which consequently can reduce air pollution, traffic congestion, and transportation cost. However, ridesharing organization requires passengers to report sensitive location information about their trips to a trip organizing server (TOS) which creates a serious privacy issue. The existing ridesharing organization schemes are neither flexible nor scalable in the sense that they require a driver and a rider to have exactly the same trip to share a ride, and they are inefficient if applied to large geographic areas. In this paper, we propose two efficient privacy-preserving ridesharing organization schemes for Non-transferable Ridesharing Service (NRS) and Transferable Ridesharing Service (TRS). In NRS, a rider shares a ride from his/her trip's start to the destination with only one driver, whereas, in TRS, a rider can transfer between multiple drivers while en route until he reaches his destination. In the proposed schemes, the ridesharing area is divided into a number of small geographic areas, called cells, and each cell has a unique identifier. Each driver/rider should encrypt his/her trip's data with modified kNN encryption scheme, and send an encrypted ridesharing offer/request to the TOS. In NRS scheme, Bloom filters are used to represent the trip information compactly before encryption. Then, the TOS can measure the similarity of the encrypted trips to organize shared rides without revealing either the users' identities or the locations. In TRS scheme, drivers report their encrypted routes, and then the TOS builds a directed graph that is passed to a modified version of Dijkstra's shortest path algorithm to search for an optimal path for rides that can achieve a set of preferences prescribed by the riders. Although TRS can be used to organize non-transferable trips, performance evaluation shows that NRS requires less communication overhead than TRS. Our formal privacy proof and analysis demonstrate that the proposed schemes can preserve users privacy and our experimental results using routes extracted from real maps show that the proposed schemes can be used efficiently for large cities.

The unprecedented growth of decentralized technologies and the abundance of healthcare data creates numerous opportunities for the digital healthcare industry and poses major challenges for data security. In this paper, we propose a novel decentralized blockchain-based medical data marketplace in which medical record sellers can sell their data to interested buyers, e.g., pharmaceutical corporations. Sellers use a smart contract to exchange their records with buyers for a digital currency. In our model, sellers can enforce flexible access control policy on the encrypted records while allowing the buyers to verify the correctness of the encrypted records without revealing any information about the records using the developed zk-SNARK protocol. In addition, sellers acquire a proof-of-delivery to redeem buyers' contingent payments by exchanging a record access key for a buyer signature using the developed trustless zero-knowledge contingent payment protocol. Our security analysis proves that our model is secure against malicious behaviors of both dishonest sellers/buyers. Performance evaluation indicates that the GAS cost on Etherume blockchain and the computational cost of the cryptographic operations are low.

Advanced metering infrastructure (AMI) networks allow utility companies to collect fine-grained power consumption data of electricity consumers for load monitoring and energy management. This brings serious privacy concerns since the fine-grained power consumption data can expose consumers' activities. Privacy-preserving data aggregation techniques have been used to preserve consumers' privacy while allowing the utility to obtain only the consumers total consumption. However, most of the existing schemes do not consider the multidimensional nature of power consumption in which electricity consumption can be categorized based on the consumption type. They also do not consider multisubset data collection in which the utility should be able to obtain the number of consumers whose consumption lies within a specific consumption range, and the overall consumption of each set of consumers. In this article, we propose an efficient and privacy-preserving multidimensional and multisubset data collection scheme, named “MDMS. ” In MDMS, the utility can obtain the total power consumption as well as the number of consumers of each subset in each dimension. In addition, for better scalability, MDMS allows the utility to delegate bill computation to the AMI networks' gateways using the encrypted readings and following the dynamic prices in which electricity prices are different based on both the time and the consumption type. Moreover, MDMS uses lightweight operations in encryption, aggregation, and decryption resulting in low computation and communication overheads as given in our experimental results. Our security analysis demonstrates that MDMS is secure and can resist collusion attacks that aim to reveal the consumers' readings.

In this paper, we propose EPIC, an efficient and privacy-preserving data collection scheme with EtoE data integrity verification for advanced metering infrastructure networks. Using efficient cryptographic operations, each meter should send a masked reading to the utility such that all the masks are canceled after aggregating all meters' masked readings, and thus the utility can only obtain an aggregated reading to preserve consumers' privacy. The utility can verify the aggregated reading integrity without accessing the individual readings to preserve privacy. It can also identify the attackers and compute electricity bills efficiently by using the fine-grained readings without violating privacy. Furthermore, EPIC can resist collusion attacks in which the utility colludes with a relay node to extract the meters' readings. A formal proof and probabilistic analysis are used to evaluate the security of EPIC, and ns-3 is used to implement EPIC and evaluate the network performance. In addition, we compare EPIC to existing data collection schemes in terms of overhead and security/privacy features.

The availability of high-performance computing platforms, large storage devices, and high- speed communications have boosted the popularity of cloud computing. Users exploit these capabilities by using the cloud as a repository for their data and sharing these data with others. However, since the cloud is usually owned and operated by private companies, storing sensitive data in the cloud servers raises privacy concerns. To address these concerns, privacy-preserving keyword search schemes have been developed. Nevertheless, most of the existing schemes are either inefficient for multi-data- owner settings or designed for single-data-owner settings, and becomes insecure and inefficient when used for multi-data-owner. This paper proposes an efficient multi-keyword ranked search scheme over encrypted data for multi-data-owner settings. The proposed scheme allows each data owner and each user to have a distinct key, and allows the server to efficiently search the files of different data owners using one encrypted query sent by the user. Our privacy analysis demonstrates that the proposed scheme can preserve the privacy of the data owners and users. In addition, our extensive performance evaluations demonstrate that our scheme is much more efficient than existing approaches in the literature.

In Long Term Evolution-Advanced (LTE-A) networks, Mobile Relay Nodes (MRNs) are installed in fast moving buses and trains to connect the passengers' devices to evolved Node B (eNB). However, since the MRNs and eNBs are installed in open environment, they can be compromised to launch security and privacy attacks. In this paper, we propose a privacy preserving intra Mobility Management Entity (MME) group handover scheme in LTE-A networks for repeated trips. Comparing to the existing schemes, the proposed scheme is devised to achieve the following requirements. First, the MRNs should be able to authenticate the received messages so that the messages sent from external attackers can be dropped by the MRNs rather than forwarding them to the core network. Second, the proposed scheme also aims to reduce the computational and signaling overhead and establish secure session keys. Third, the scheme aims to prevent MRNs and eNBs from tracking passengers' locations especially if they take same trip regularly. Our analysis demonstrates that the proposed scheme can achieve our security and privacy objectives. Our performance evaluations demonstrate that the proposed scheme requires a few number of messages and low computation overhead.

The autonomous vehicles will make ride sharing popular, and necessary. However, ride sharing organization requires the passengers to reveal sensitive information about their trips, which causes a serious privacy issue. In this paper, we propose a privacy-preserving ride sharing organization scheme using the kNN encryption scheme, Bloom filter, and group signature. Each user encrypts his trip's data and sends an encrypted ride-sharing request to a server that measures the similarity between users trips' to organize shared rides without revealing sensitive information. Comparing to our proposal in [1], this paper has three improvements. The proposed scheme is much more efficient because the trip data is much shorter. It is also more secure because each user has his own encryption key instead of using one shared key for all users. It can prevent linking the encryptions of the trip's data sent at different times because users frequently update their keys efficiently. Our privacy analysis demonstrates that the proposed scheme can preserve users' location privacy and trips' data privacy. Our experimental results on a real map demonstrate that the proposed scheme is much more efficient than the existing schemes, especially for large cities.