scispace - formally typeset
Search or ask a question
Author

Gang Liu

Bio: Gang Liu is an academic researcher from Xidian University. The author has contributed to research in topics: Access control & Permission. The author has an hindex of 3, co-authored 23 publications receiving 36 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: This work investigated and analysed the privacy issues between the data owners, untrustworthy third-part cloud servers, and the data users, and proposed a lightweight privacy-preserving scheme based on homomorphic encryption in the context of the IoT.
Abstract: The emerging technologies, such as smart sensors, 5G/6G wireless communication, artificial intelligence, etc., have being maturing the future Internet of Things (IoT) by connecting massive number of devices, which are expected to consistently collect and transmit real-time data to support business intelligence in an efficient and privacy-preserving way. The IoT can afford businesses predictive maintenance, improve field service, asset tracking, and further enhance customer satisfaction and facility management in industrial sectors. However, the privacy concern in IoT is a big challenge in IoT applications and services. This work proposed a lightweight privacy-preserving scheme based on homomorphic encryption in the context of the IoT, in which we investigated and analysed the privacy issues between the data owners, untrustworthy third-part cloud servers, and the data users. Meanwhile, computationally-efficient homomorphic algorithms are proposed to guarantee the privacy protection for the data users. Experimental results demonstrates that the proposed scheme can effectively prevent privacy breaches in IoT.

21 citations

Journal ArticleDOI
TL;DR: In this paper, the authors proposed an advanced softmax loss (ASL) to mitigate the bias induced by data imbalance and hence increase accuracy and reliability for facial expression recognition, which can be easily implemented in any deep network.
Abstract: An important challenge for facial expression recognition (FER) is that real-world training data are usually imbalanced. Although many deep learning approaches have been proposed to enhance the discriminative power of deep expression features and enable a good predictive effect, few works have focused on the multiclass imbalance problem. When supervised by softmax loss (SL), which is widely used in FER, the classifier is often biased against minority categories (i.e., smaller interclass angular distances). In this letter, we present advanced softmax loss (ASL) to mitigate the bias induced by data imbalance and hence increase accuracy and reliability. The proposed ASL essentially magnifies the interclass diversity in the angular space to enhance discriminative power in every category. The proposed loss can easily be implemented in any deep network. Extensive experiments on the FER2013 and real-world affective faces (RAF) databases demonstrate that ASL is significantly more accurate and reliable than many state-of-the-art approaches and that it can easily be plugged into other methods and improves their performance.

15 citations

Journal ArticleDOI
TL;DR: In this paper, the authors proposed ABSAC, which is a secure anonymous access framework for Internet of Things (IoT) devices that preserves user privacy while guaranteeing scalability and efficiency.
Abstract: Smart cities require new access control models for Internet of Things (IoT) devices that preserve user privacy while guaranteeing scalability and efficiency. Researchers believe that anonymous access can protect the private information even if the private information is not stored in authorization organization. Many attribute-based access control (ABAC) models that support anonymous access expose the attributes of the subject to the authorization organization during the authorization process, which allows the authorization organization to obtain the attributes of the subject and infer the identity of the subject. The ABAC with anonymous access proposed in this paper called ABSAC strengthens the identity-less of ABAC by combining homomorphic attribute-based signatures (HABSs) which does not send the subject attributes to the authorization organization, reducing the risk of subject identity re-identification. It is a secure anonymous access framework. Tests show that the performance of ABSAC implementation is similar to ABAC’s performance.

11 citations

Journal ArticleDOI

[...]

Gang Liu1, Runnan Zhang1, Huimin Song1, Can Wang1, Jinhui Liu1, Aijun Liu 
TL;DR: A new independent mechanism is proposed, termed transformation, which can change the user assignment to achieve dynamic changes in user permissions to create a new model called the Ts-RBAC model, which maintains the safety ensured by the BTG- RBAC model and improves the flexibility of the system.

9 citations

Journal ArticleDOI
TL;DR: Zhang et al. as mentioned in this paper proposed a multiscale and multidirectional network named the Contourlet convolutional neural network (CCNN) for synthetic aperture radar (SAR) image despeckling.
Abstract: A multiscale and multidirectional network named the Contourlet convolutional neural network (CCNN) is proposed for synthetic aperture radar (SAR) image despeckling. SAR image resolution is not higher than that of optical images. If the network depth is increased blindly, the SAR image detail information flow will become quite weak, resulting in severe vanishing/exploding gradients. In this paper, a multiscale and multidirectional convolutional neural network is constructed, in which a single-stream structure of convolutional layers is replaced with a multiple-stream structure to extract image features with multidirectional and multiscale properties, thus significantly improving the despeckling performance. With the help of the Contourlet, the CCNN is designed with multiple independent subnetworks to respectively capture abstract features of an image in a certain frequency and direction band. The CCNN can increase the number of convolutional layers by increasing the number of subnetworks, which makes the CCNN not only have enough convolutional layers to capture the SAR image features, but also overcome the problem of vanishing/exploding gradients caused by deepening the networks. Extensive quantitative and qualitative evaluations of synthetic and real SAR images show the superiority of our proposed method over the state-of-the-art speckle reduction method.

9 citations


Cited by
More filters
Journal Article
TL;DR: In this paper, the authors suggest the use of an access control policy language which allows for override of denied access in some cases for increased flexibility, and they suggest that the overrides should be audited and the policy can be used for finding the people who should perform the audit.
Abstract: Because it is difficult to predict access needs in advance and the limitations of formal policy languages it is difficult to completely define an access control policy ahead of the actual use. We suggest the use of an policy language which allows for override of denied access in some cases for increased flexibility. The overrides should be audited and we suggest that the access control policy can be used for finding the people who should perform the audit.

42 citations

Journal ArticleDOI
TL;DR: This work proposes a model named Two-branch Disentangled Generative Adversarial Network (TDGAN) for discriminative expression representation learning, which learns to disentangle expressional information from other unrelated facial attributes.
Abstract: Facial Expression Recognition (FER) is a challenging task in computer vision as features extracted from expressional images are usually entangled with other facial attributes, e.g., poses or appearance variations, which are adverse to FER. To achieve a better FER performance, we propose a model named Two-branch Disentangled Generative Adversarial Network (TDGAN) for discriminative expression representation learning. Different from previous methods, TDGAN learns to disentangle expressional information from other unrelated facial attributes. To this end, we build the framework with two independent branches, which are specific for facial and expressional information processing respectively. Correspondingly, two discriminators are introduced to conduct identity and expression classification. By adversarial learning, TDGAN is able to transfer an expression to a given face. It simultaneously learns a discriminative representation that is disentangled from other facial attributes for each expression image, which is more effective for FER task. In addition, a self-supervised mechanism is proposed to improve representation learning, which enhances the power of disentangling. Quantitative and qualitative results in both in-the-lab and in-the-wild datasets demonstrate that TDGAN is competitive to the state-of-the-art methods.

41 citations

Journal ArticleDOI
TL;DR: This work proposes an enhanced Bell–LaPadula model and categorized the peers and transactions in different clearance and security levels and constructed a dynamic access control policies using a smart contracts to provide data security in the network.
Abstract: Access control is a policy in data security that controls access to resources. The current access control mechanisms are facing many problems, due to the interference of the third-party, privacy, and security of data. These problems can be addressed by blockchain, the technology that gained major attention in recent years and has many capabilities. However, in the blockchain network, every peer maintains the same state of the ledger to view the complete history of transactions that leads to scalability issues in the blockchain network. To address the problem of scalability we propose an enhanced Bell–LaPadula model and categorized the peers and transactions in different clearance and security levels. The peers don’t have to maintain the complete history of transactions owing to the clearance level. To provide data security in the network we constructed a dynamic access control policies using a smart contracts. We test our model on a blockchain-based healthcare network. The Hyperledger Fabric tool is used to run a complete infrastructure of healthcare organization while the Hyperledger composer modeling tool is used to implement the smart contracts and to provide dynamic access control functionality on the blockchain network.

31 citations

Journal ArticleDOI
TL;DR: A high-level overview in an organized fashion of radiation effects on electronics; design techniques to minimize such effects; and modeling and simulation tools available is provided to provide a comprehensive coverage on this subject.

28 citations

Journal ArticleDOI
TL;DR: In this paper , a lightweight A-MobileNet model is proposed to enhance the local feature extraction of facial expressions, where the center loss and softmax loss are combined to optimize the model parameters to reduce intra-class distance and increase interclass distance.
Abstract: Facial expression recognition (FER) is to separate the specific expression state from the given static image or video to determine the psychological emotions of the recognized object, the realization of the computer's understanding and recognition of facial expressions have fundamentally changed the relationship between human and computer, to achieve better human computer interaction (HCI). In recent years, FER has attracted widespread attention in the fields of HCI, security, communications and driving, and has become one of the research hotspots. In the mobile Internet era, the need for lightweight networking and real-time performance is growing. In this paper, a lightweight A-MobileNet model is proposed. First, the attention module is introduced into the MobileNetV1 model to enhance the local feature extraction of facial expressions. Then, the center loss and softmax loss are combined to optimize the model parameters to reduce intra-class distance and increase inter-class distance. Compared with the original MobileNet series models, our method significantly improves recognition accuracy without increasing the number of model parameters. Compared with others, A- MobileNet model achieves better results on the FERPlus and RAF-DB datasets.

27 citations