Emotion recognition from electroencephalography (EEG) signals is an important component of emotionally intelligent human–computer interaction systems. However, existing approaches often rely on handcrafted features or conventional deep learning architectures that struggle to generalize across subjects due to the high variability of EEG signals. Most prior studies focus primarily on binary emotion classification and provide limited investigation of more complex multi-class scenarios. This work presents EmoCaps, an end-to end deep learning framework based on a capsule network with a self-attention–guided routing mechanism to learn discriminative representations directly from raw EEG signals. The proposed model is evaluated on the DEAP dataset under both subject dependent and subject-independent settings and across binary and multi-class emotion recognition tasks involving valence, arousal, and dominance dimensions. Experimental results demonstrate that EmoCaps consistently outperforms several representative deep learning models. In subject-dependent binary classification, the proposed approach achieves accuracies of up to 97%, while in the more challenging subject-independent setting it exceeds 80% accuracy across emotional dimensions. The framework also achieves strong performance in four-class and eight-class emotion recognition tasks and provides, to the best of our knowledge, the first reported results for subject independent multi-class emotion recognition on this dataset. Although the capsule-based architecture introduces higher computational cost, the proposed model significantly improves robustness and generalization across subjects. These results highlight the potential of EmoCaps for real-world emotion-aware applications in healthcare, adaptive learning, and affective computing systems.

For wearable devices with constrained computational resources, it is typically required to offload processing tasks to more capable servers. However, this practice introduces vulnerabilities to data confidentiality and integrity due to potential malicious network attacks, unreliable servers, and insecure communication channels. A robust mechanism that ensures anonymous authentication and key agreement is therefore imperative for safeguarding the authenticity of computing entities and securing data during transmission. Recently, Guoet al.proposed an anonymous authentication key agreement and group proof protocol specifically designed for wearable devices. This protocol, benefiting from the strengths of previous research, is designed to thwart a variety of cyber threats. However, inaccuracies in their protocol lead to issues with authenticity verification, ultimately preventing the establishment of secure session keys between communication entities. To address these design flaws, an improved ultra-lightweight protocol was proposed, employing cryptographic hash functions to ensure authentication and privacy during data transmission in wearable devices. Supported by rigorous security validations and analyses, the proposed protocol significantly boosts both security and efficiency, marking a substantial advancement over prior methodologies.

The surge in smartphone and wearable device usage has propelled the advancement of the Internet of Things (IoT) applications. Among these, e-healthcare stands out as a fundamental service, enabling the remote access and storage of patient-related data on a centralized medical server (MS), and facilitating connections between authorized individuals such as doctors, patients, and nurses over the public Internet. However, the inherent vulnerability of the public Internet to diverse security threats underscores the critical need for a robust and secure user authentication protocol to safeguard these essential services. This research presents a novel, resource-efficient user authentication protocol specifically designed for healthcare systems. Our proposed protocol leverages the lightweight authenticated encryption with associated data (AEAD) primitive Ascon combined with hash functions and XoR, specifically tailored for encrypted communication in resource-constrained IoT devices, emphasizing resource efficiency. Additionally, the proposed protocol establishes secure session keys between users and MS, facilitating future encrypted communications and preventing unauthorized attackers from illegally obtaining users' private data. Furthermore, comprehensive security validation, including informal security analyses, demonstrates the protocol's resilience against a spectrum of security threats. Extensive analysis reveals that our proposed protocol significantly reduces computational and communication resource requirements during the authentication phase in comparison to similar authentication protocols, underscoring its efficiency and suitability for deployment in healthcare systems.

Collaborative resource scheduling between edge terminals and cloud centers is regarded as a promising means of effectively completing computing tasks and enhancing quality of service. In this paper, to further improve the achievable performance, the edge cloud resource scheduling (ECRS) problem is transformed into a multi-objective Markov decision process based on task dependency and features extraction. A multi-objective ECRS model is proposed by considering the task completion time, cost, energy consumption and system reliability as the four objectives. Furthermore, a hybrid approach based on deep reinforcement learning (DRL) and multi-objective optimization are employed in our work. Specifically, DRL preprocesses the workflow, and a multi-objective optimization method strives to find the Pareto-optimal workflow scheduling decision. Various experiments are performed on three real data sets with different numbers of tasks. The results obtained demonstrate that the proposed hybrid DRL and multi-objective optimization design outperforms existing design approaches.

Wearable computing has shown tremendous potential to revolutionize and uplift the standard of our lives. However, researchers and field experts have often noted several privacy and security vulnerabilities in the field of wearable computing. In order to tackle these problems, various schemes have been proposed in the literature to improve the efficiency of authentication and key establishment procedure. However, the existing schemes have relatively high computation and communication overheads and are not resilient to various potential security attacks, which reduces their significance for applicability in constrained wearable devices. In this work, we propose an efficient and anonymous authenticated key exchange scheme for wearable computing (EAKE-WC), which performs mutual authentication between the user and the wearable device, and between the cloud server and the user. It also establishes secret session keys for each session to secure communication among the communicating entities. Additionally, the proposed EAKE-WC scheme is designed using authenticated encryption with associated data (AEAD) primitives like ASCON, bitwise XOR, and hash functions. Our results from the security analysis depict compliance of the proposed EAKE-WC with wearable computing's security criteria. In addition, we also demonstrate through a comprehensive comparative analysis that the proposed scheme, EAKE-WC, outperforms the existing benchmark schemes in various key performance areas, including lower communication and computational overheads, enhanced security, and added functionality.

An edge cloud architecture plays a key role in improving the user task computing service system by combining the powerful data processing capability of cloud centres with the low latency of edge computing. Existing methods for maximizing the efficiency of an edge cloud architecture take into account time and task parameters but ignore other factors such as load balancing, cost, and user satisfaction when scheduling resources. In this work, we propose a many-objective resource scheduling model for optimizing the performance of an edge cloud architecture, which takes into account the time spent on task, cost, load balance, user satisfaction, and trust measurement. The resource scheduling model converges to the optimal solution using a novel many-objective ensemble optimization algorithm based on a dynamic selection mechanism. The study also explores the support set convergence of eight evolutionary operators using the ensemble algorithm. The model solutions are dynamically updated with the help of the dynamic integration probability, and then a selection criteria is used to pick the best solutions from the pool of generated solutions. Two simulations on a benchmark dataset are used to verify the usefulness and performance of the designed algorithm. Our approach was able to locate more than half of the best solutions on the benchmark functions, and it also showed to be a better model solution than the some of the popular many-objective algorithms for dealing with the edge cloud resource scheduling problem, according to the results obtained from the simulations.

Delayed delivery of packets hinders the performance of time-sensitive Internet of Things (IoT) applications and incurs increased power consumption. Stochastic routing schemes solve the problem of saving all participating nodes from getting their power drained out quickly. However, stochastic routing incurs the problem of delivery delays and reliable end-to-end delivery. This paper proposes a novel routing scheme, called $Q_{i j}$ routing, to solve these problems. The proposed $Q_{i j}$ routing scheme is a combination of a classic routing scheme, called Distance Vector Algorithm, with a novel re-definition of the cost of a link to find the best path from source to destination. $Q_{i j}$ takes into account the wireless link reliability of any connection between two nodes, and the transmission delay of IoT devices working together in a distributed network. With the presented mathematical model, a routing table is maintained that let an individual node in a network find the distinctly prominent reliable path among many routes from source to destination. The superior efficiency of $Q_{i j}$ routing scheme over eminent stochastic routing schemes is proven through simulation results in terms of reduced end-to-end expected delivery delay and increased expected delivery ratio.

This research aims to design a smart parking system using cloud and Internet of Things (IoT) technologies to improve the process of finding parking spaces in urban areas. The proposed system utilizes sensors and microcontrollers in each parking space to provide real-time data to users through a mobile application. The primary objective of our research is to address issues, such as time-consuming manual searches for parking spaces and reduce traffic congestion. This research suggests a system of reliable smart ultra-sonic sensors connected to a microcontroller for easy and remote parking automation. Users can select a parking space by clicking on the available slot in the mobile application. Additionally, the mobile application informs users about empty spots. This smart parking system can be implemented on both small and large-scale models, and the results suggest that it effectively replicates traditional automobile parking, with the added convenience of a mobile application, in urban areas.

Wireless sensor networks have become incredibly popular due to the Internet of Things’ (IoT) rapid development. IoT routing is the basis for the efficient operation of the perception-layer network. As a popular type of machine learning, reinforcement learning techniques have gained significant attention due to their successful application in the field of network communication. In the traditional Routing Protocol for low-power and Lossy Networks (RPL) protocol, to solve the fairness of control message transmission between IoT terminals, a fair broadcast suppression mechanism, or Drizzle algorithm, is usually used, but the Drizzle algorithm cannot allocate priority. Moreover, the Drizzle algorithm keeps changing its redundant constant k value but never converges to the optimal value of k. To address this problem, this paper uses a combination based on reinforcement learning (RL) and trickle timer. This paper proposes an RL Intelligent Adaptive Trickle-Timer Algorithm (RLATT) for routing optimization of the IoT awareness layer. RLATT has triple-optimized the trickle timer algorithm. To verify the algorithm’s effectiveness, the simulation is carried out on Contiki operating system and compared with the standard trickling timer and Drizzle algorithm. Experiments show that the proposed algorithm performs better in terms of packet delivery ratio (PDR), power consumption, network convergence time, and total control cost ratio.

With the widespread popularity of mobile terminals in the Internet of Things (IoT), the demand for cross-domain access of mobile terminals between different regions has also increased significantly. The nature of wireless communication media makes mobile terminals vulnerable to security threats in cross-domain access. Identity authentication is a prerequisite for secure data transmission in the cross-domain, and it is also the first step to guarantee the credibility of data sources. Most existing authentication schemes are based on bilinear pairing or public-key encryption and decryption with high computation overhead, which are not suitable for the resource-limited mobile IoT terminals. Moreover, these schemes have some security drawbacks and cannot meet the security requirements of cross-domain access. In this article, we propose a lightweight cross-domain mutual identity authentication (LCDMA) for the mobile IoT environment. LCDMA uses a symmetric polynomial instead of high-complexity bilinear pairing in the traditional schemes. We theoretically analyze the security performance under the random oracle model. Our results show that LCDMA not only resists common attacks but also preserves secure traceability while guaranteeing anonymity. Performance evaluation further demonstrates that our scheme has better performance in terms of computation and communication overhead, compared with other existing representative schemes.

In-vehicle network security plays a vital role in ensuring the secure information transfer between vehicle and Internet. The existing research is still facing great difficulties in balancing the conflicting factors for the in-vehicle network security and hence to improve intrusion detection performance. To challenge this issue, we construct a many-objective intrusion detection model by including information entropy, accuracy, false positive rate and response time of anomaly detection as the four objectives, which represent the key factors influencing intrusion detection performance. We then design an improved intrusion detection algorithm based on many-objective optimization to optimize the detection model parameters. The designed algorithm has double evolutionary selections. Specifically, an improved differential evolutionary operator produces new offspring of the internal population, and a spherical pruning mechanism selects the excellent internal solutions to form the selected pool of the external archive. The second evolutionary selection then produces new offspring of the archive, and an archive selection mechanism of the external archive selects and stores the optimal solutions in the whole detection process. An experiment is performed using a real-world in-vehicle network data set to verify the performance of our proposed model and algorithm. Experimental results obtained demonstrate that our algorithm can respond quickly to attacks and achieve high entropy and detection accuracy as well as very low false positive rate with a good trade-off in the conflicting objective landscape.

The proliferation of Internet of Things (IoT) devices in the 5G era has resulted in increased security vulnerabilities and zero-day attacks, underscoring the importance of network intrusion detection systems (NIDS). However, existing NIDS have limitations in terms of accuracy, recall rates, false alarm rates, and generalization capabilities, and they cannot meet the IoT's requirements for low latency and limited computing resources. To overcome these challenges, we propose a NIDS based on a pseudo-siamese stacked autoencoder (PSSAE), deployed in the fog computing layer. Our system uses unsupervised training of stacked autoencoders (SAEs) to extract deep semantic features of normal and abnormal traffic, followed by supervised learning with labels to improve characterization and classification capabilities. The results show that our proposed method's accuracy and detection rate (DR) is 2% to 15% and 1%–14% higher than the existing techniques using the KDDTest+ dataset, respectively. Our proposed method outperformed the existing methods by 1% to 4% using the KDDTest+ dataset. The F1-Score is higher by 3%–11.55% using the KDDTest+ dataset. On the other hand, using the KDDTest-21 dataset, the accuracy of our proposed method also outperformed the existing technique by 6.09%–13.81%. The DR and F1-Score are higher by 7.02% and 5.57%, respectively, using the KDDTest+ dataset. This is due to the fact that each layer of the network trained by SAEs is more capable of extracting the semantic features of the data than the DNN-trained network directly.

Mobile edge computing (MEC) is an effective computing tool to cope with the explosive growth of data traffic. It plays a vital role in improving the quality of service for user task computing. However, the existing solutions rarely address all the significant factors that impact the quality of service. To challenge this problem, a trusted many-objective model is built by comprehensively considering the task time delay, server energy consumption, trust metrics between task and server, and user experience utility factors in multi-server MEC networks. We decompose the original problem into task offloading (TO) and resource allocation (RA) to address the model. Then a novel hybrid many-objective optimization algorithm based on cascading clustering and incremental learning is designed to optimize the TO decision solutions. A low-complexity heuristic method is adopted based on the optimal TO decision solutions to optimize the RA problem continuously. To verify the model's validity and the optimisation algorithm's superiority, five other advanced many-objective algorithms are used for comparison. The results show that our algorithm has more than half the number of the superior values for the benchmark problem. And the obtained model solution shows good performance on different indicators metrics for the decomposition problem.

Internet of Things (IoT) is a promising technology that attains significant consideration in diverse industrial areas, i.e., agriculture, engineering, logistics, trading, ecological examining, security surveillance, energy, and healthcare. IoT gains much more attention with the rapid advancement of wireless communication and sensor networks as millions of intelligent devices get involved in IoT. These intelligent devices' raw data must be captured and processed to support decision-making. However, IoT applications trust the central server for information storage, processing, and mediators for wireless transmission. Consequently, it can leak the information and lead to high costs and delays. Hence, data security is the leading interest for the IoT. Blockchain technology can be deployed to overcome the security and effectiveness of the gigantic data in IoT. Blockchain is studied as a key to permitting storing, processing and sharing of data in an efficient, secure manner. In addition, reinforcement learning can convene the high data rate requirements. It will help us to optimize the performance of the blockchain-enabled IoT framework.

Mobile edge computing (MEC) is used for compu-tationally complex applications by offloading it to the nearby edge server either partially or entirely. The problem arises of selecting whether the component is to be offloaded to the mobile edge server (MES) for execution, or it needs to be executed locally. Therefore, we propose a time-efficient decision offloading scheme (TEDOS) to derive a data set and train an artificial neural network (ANN) on the derived data set. TEDOS provide the smart decision on the optimal permutation of the divided components based on delay. We developed a mathematical model for delays in communication, execution and component queuing. We obtained a final delay for all possible permutations of component offloading policies. Our model obtained 91 % accurate results as compared to the existing schemes. The simulation result shows that our proposed model outperforms the state-of-the-art.

Glioma is the most aggressive and dangerous primary brain tumor with a survival time of less than 14 months. Segmentation of tumors is a necessary task in the image processing of the gliomas and is important for its timely diagnosis and starting a treatment. Using 3D U-net architecture to perform semantic segmentation on brain tumor dataset is at the core of deep learning. In this paper, we present a unique cloud-based 3D U-Net method to perform brain tumor segmentation using BRATS dataset. The system was effectively trained by using Adam optimization solver by utilizing multiple hyper parameters. We got an average dice score of 95% which makes our method the first cloud-based method to achieve maximum accuracy. The dice score is calculated by using Sørensen-Dice similarity coefficient. We also performed an extensive literature review of the brain tumor segmentation methods implemented in the last five years to get a state-of-the-art picture of well-known methodologies with a higher dice score. In comparison to the already implemented architectures, our method ranks on top in terms of accuracy in using a cloud-based 3D U-Net framework for glioma segmentation.

With the rapid development of wireless communication technologies, the emerging multimedia applications make mobile Internet traffic grow explosively while putting forward higher service requirements for the next-generation wireless networks. Therefore, how to achieve low-latency content transmission by effectively allocating heterogeneous network resources to improve the network quality of service and end-user quality of experience is a key issue to be solved urgently in the current Internet. In this article, we propose a deep reinforcement learning (DRL)-based resource allocation scheme to improve content distribution in a layered fog radio access network (FRAN). We formulate the optimal resource allocation problem as a minimal delay model, where in-network caching is deployed and the same content requests from mobile users can be aggregated in the queue of each base station. To cope with the increasing user requests and overcome capacity constraints of the FRAN, moreover, a cloud–edge cooperation offloading scheme is utilized in our model, where the integrated allocation of caching, computing, and communication resources and joint optimization between in-network caching and routing are considered to promote resource utilization and content delivery. In our solution, a new DRL policy is designed to make cross-layer cooperative caching and routing decisions for the arriving content requests according to request history information and available network resources in the system. Simulation results demonstrate that our proposed model can performs much better than the existing cloud–edge cooperation schemes in the FRAN.

Fog computing is an emerging technology that aims at reducing the load on cloud data centers by migrating some computation and storage toward end-users. It leverages the intermediate servers for local processing and storage while making it possible to offload part of the computation and storage to the cloud. Inspired by the benefits of fog computing, we present a novel paradigm that considers the context of social phenomena. Online and off-line human interactions and the mobile social network’s relentless growth allowed real-world data and created users’ traces. We categorize social phenomena into two main groups to integrate with fog computing from social interactions’ continuous development. In this regard, the first contribution addresses the social relationship between the end-users and fog nodes based on personal benefits. The social relationship considers trust, reciprocity, incentives, and selfishness mechanisms. The second contribution describes the group-based social behavior, i.e., centrality, community, and colocation in fog computing networks (FCNs). We also discuss the impact of social phenomena on FCNs in network performance, resource allocations, security, and privacy. We present open challenges and highlight future directions on social perception to encourage follow-up work.

The rapid growth of various vehicular apps such as automotive navigation and in-car entertainment has brought the explosion of vehicular data. Such a growth has given rise to a huge challenge of maintaining the quality of cloud storage services for the whole period of storage in vehicular networks. As a result, poor quality of services easily causes data corruption problems and thereby threats vehicular data integrity. Blockchain, a tamper-proofing technique, is considered a promising approach for mitigating data integrity risks in cloud storage. However, existing blockchain-based schemes for auditing long-term cloud data integrity suffer from poor communication performance in a vehicular network. In this study, a blockchain-based offline auditing scheme for cloud storage in the vehicular network is proposed to improve auditing performance. Inspired by the data structure of blockchain, we design an evidence chain to achieve offline auditing, which allows the cloud to spontaneously generate data integrity evidence without communicating with auditors during the evidence generation phase. Furthermore, we extend our scheme to support public and automatic validation based on the smart contract. We prove the security of the proposed scheme under the random oracle model and further provide the performance evaluation by comparing with the state-of-the-art approaches.

The modern computing applications are presently adapting to the convenient availability of huge and diverse data for making their pattern recognition methods smarter. Identification of dominant emotion solely based on the text data generated by humans is essential for the modern human–computer interaction. This work presents a multimodal text-keystrokes dataset and associated learning methods for the identification of human emotions hidden in small text. For this, a text-keystrokes data of 69 participants is collected in multiple scenarios. Stimuli are induced through videos in a controlled environment. After the stimuli induction, participants write their reviews about the given scenario in an unguided manner. Afterward, keystroke and in-text features are extracted from the dataset. These are used with an assortment of learning methods to identify emotion hidden in the short text. An accuracy of 86.95% is achieved by fusing text and keystroke features. Whereas, 100% accuracy is obtained for pleasure-displeasure classes of emotions using the fusion of keystroke/text features, tree-based feature selection method, and support vector machine classifier. The present work is also compared with four state-of-the-art techniques for the same task, where the results suggest that the present proposal performs better in terms of accuracy.

Millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) offers a promising technique to fulfil the high data demand and connectivity of the Internet-of-Things (IoT) and 5G communications because it owns valuable and unknown spectrum resources. Using massive antennas with recently introduced drone-enabled aerial computing platforms, named unmanned aerial vehicles (UAVs), can cast high energy consumption if fully-digital precoding is employed at the UAVs. Using hybrid precoding at a UAV can reduce hardware complexity and energy consumption but is challenging with a need for joint optimization of three precoding matrices at the UAV (sixth-order polynomial objective function). In this paper, we propose to decompose the original UAV hybrid precoding challenge into three subproblems and develop a coordinated descent optimization (CDO) algorithm to solve the three problems recursively. In addition, the convergence and complexity of this new technique are analyzed. Numerical studies indicate the improved effectiveness of the proposed solution over existing solutions.

Cognitive radio networks (CRNs) promise to accommodate billions of Internet of Things (IoT) devices within scarce spectrum by allowing secondary users (SUs) to use licensed spectrum. However, the devices need uninterruptible communication, which the conventional CRNs cannot fulfill. This necessitates successful service completion probability (SSCP) enhancement in CRNs. Further, maintaining fairness among SUs, in terms of availing network services, is a matter of consideration for ensuring the network services to be fairly available to all SUs. In this paper, we propose a hybrid CRN (HCRN) scheme to analyze two problems. Firstly, we investigate SSCP enhancement by utilizing hybrid underlay-interweave mode of CRNs and propose a dynamic channel reservation algorithm to support interrupted users. Secondly, we propose a multi-attributes based fairness-driven channel determination (MFD) algorithm for channel interruption, which ensures fairness among SUs in availing network services. Furthermore, continuous-time Markov chain is used for modelling, and mathematical formulations are derived for SSCP. The proposed scheme is evaluated under various network traffic loads and channel failure rates. Numerical results show significant improvement in SSCP and reduction in forced termination rate as compared to the benchmark. Similarly, the MFD algorithm brings a prominent improvement in fairness.

The intrinsic broadcast nature of wireless communication let the attackers to initiate several passive attacks such as eavesdropping. In this attack, the attackers do not disturb/stop or interrupt the communication channel, but it will silently steal the information between authentic users. For this purpose, physical layer security (PLS) is one of the promising methodologies to secure wireless transmissions from eavesdroppers. However, PLS is further divided into keyless security and secret key‐based security. The keyless security is not practically implemented because it requires full/part of instantaneous/statistical channel state information (CSI) of the eavesdroppers. Alternatively, key‐based security is exploiting the randomness and reciprocity of wireless channels that do not require any CSI from an eavesdropper. The secret key‐based security is due to the unpredictability of wireless channels between two users. However, the secret key‐based security mainly on two basic parameters, i.e. coherence time and transmission power. Nevertheless, the wireless channel between users has a short coherence time, and it will provide shorter keys' length due to which eavesdropper can easily extract keys between communicating parties. To overcome this limitation, we proposed the power allocation scheme to improve the secret key generation rate (SKGR) to strengthen the security between authentic users.

Training of the convolution neural network (CNN) is a problem of global optimisation. This study proposed a hybrid modified particle swarm optimisation (MPSO) and conjugate gradient (CG) algorithm for efficient training of CNN. The training involves MPSO–CG to avoid trapping in local minima. Particularly, improvements in the MPSO by introducing a novel approach for control parameters, improved parameters updating criteria, a novel parameter in the velocity update equation, and fusion of the CG allows handling the issues in training CNN. In this study, the authors validate the proposed MPSO algorithm on three benchmark mathematical test functions and also compared with three different variants of the baseline particle swarm optimisation algorithm. Furthermore, the performance of the proposed MPSO–CG is also compared with other training algorithms focusing on the analysis of computational cost, convergence, and accuracy based on a standard problem specific to classification applications on CIFAR‐10 dataset and face and skin detection dataset.

In future small cell networks, tracking areas (TAs) that are defined for location management will be updated frequently to cope with the massive signalling overhead. In this study, a TA planning method based on spectral clustering is proposed to minimise the network signalling overhead. Firstly, handover and paging statistics are simulated to construct a series of graphs showing user mobility and traffic. Then, the TA planning problem is formulated as a classical graph partitioning problem. Finally, a new TA planning method based on spectral clustering is used to build the new TA plan. Simulation results show that the proposed method can effectively reduce the system location update rate and signalling overhead, and improve the system performance.

Summary In recent years, more and more companies outsource their data to the cloud service provider to greatly reduce the cost. However, it also raises underlying security and privacy issues for the significant corporate data. Therefore, a natural way to keep sensitive data confidential against an untrusted cloud service provider is only to store the encrypted data in the cloud. Flexible encryption schemes can provide a fine grain access control for the encrypted data and ensure legitimate user to decrypt the corresponding data. The key problems of this approach include establishing access control for the encrypted data and revoking the access rights from users when they are no longer authorized to access the encrypted data on cloud servers. This paper aims to solve these problems. First, with the attribute encryption and the dual encryption system, we propose a concrete access control scheme constructed over the composite‐order bilinear groups, and we prove its security under the standard model. Then, we propose a fully fine‐grained revocation scheme under the direct revocation model so as to efficiently revoke access rights from users on cloud servers. Copyright © 2012 John Wiley & Sons, Ltd.