Deep learning model is a multi-layered network structure, and the network parameters that evaluate the final performance of the model must be trained by a deep learning optimizer. In comparison to the mainstream optimizers that utilize integer-order derivatives reflecting only local information, fractional-order derivatives optimizers, which can capture global information, are gradually gaining attention. However, relying solely on the long-term estimated gradients computed from fractional-order derivatives while disregarding the influence of recent gradients on the optimization process can sometimes lead to issues such as local optima and slower optimization speeds. In this paper, we design an adaptive learning rate optimizer called AdaGL based on the Grünwald–Letnikov (G–L) fractional-order derivative. It changes the direction and step size of parameter updating dynamically according to the long-term and short-term gradients information, addressing the problem of falling into local minima or saddle points. To be specific, by utilizing the global memory of fractional-order calculus, we replace the gradient of parameter update with G–L fractional-order approximated gradient, making better use of the long-term curvature information in the past. Furthermore, considering that the recent gradient information often impacts the optimization phase significantly, we propose a step size control coefficient to adjust the learning rate in real-time. To compare the performance of the proposed AdaGL with the current advanced optimizers, we conduct several different deep learning tasks, including image classification on CNNs, node classification and graph classification on GNNs, image generation on GANs, and language modeling on LSTM. Extensive experimental results demonstrate that AdaGL achieves stable and fast convergence, excellent accuracy, and good generalization performance.
Edge computing has been introduced to the Internet of Things (IoT) to meet the requirements of IoT applications. At the same time, data aggregation is widely used in data processing to reduce the communication overhead and energy consumption in IoT. Most existing schemes aggregate the overall data without filtering. In addition, aggregation schemes also face huge challenges, such as the privacy of the individual IoT device’s data or the fault-tolerant and lightweight requirements of the schemes. In this paper, we present a privacy-preserving and lightweight selective aggregation scheme with fault tolerance (PLSA-FT) for edge computing-enhanced IoT. In PLSA-FT, selective aggregation can be achieved by constructing Boolean responses and numerical responses according to specific query conditions of the cloud center. Furthermore, we modified the basic Paillier homomorphic encryption to guarantee data privacy and support fault tolerance of IoT devices’ malfunctions. An online/offline signature mechanism is utilized to reduce computation costs. The system characteristic analyses prove that the PLSA-FT scheme achieves confidentiality, privacy preservation, source authentication, integrity verification, fault tolerance, and dynamic membership management. Moreover, performance evaluation results show that PLSA-FT is lightweight with low computation costs and communication overheads.
With the continuous development of the Vehicular Ad Hoc Network (VANET), cross-domain sharing of vehicle data has become a significant concern. The Ciphertext-Policy Attribute-Based Encryption (CP-ABE) algorithm plays a key role in data sharing as it can achieve “one-to-many” transmission. In this paper, we propose a cross-domain data sharing scheme based on unpaired CP-ABE in VANETs, utilizing the blockchain and InterPlanetary File System (IPFS) system. The blockchain network is composed of trusted authorities (TAs) from different domains. Due to the high-speed movement characteristics of vehicles, we divide vehicle attributes into two categories: static and dynamic. we design a cross-domain data verification contract based on attribute bloom filter (ABF) for decryption testing. Vehicles that pass the test will receive dynamic attribute decryption keys generated by TAs in the data sharing domain to achieve cross-domain access. In addition, we design an outsourced decryption scheme to reduce the computational overhead during vehicle decryption and propose a direct permission revocation mechanism to ensure the flexibility and security of the system. The simulation experiment results show that our scheme optimizes the efficiency of cross-domain data access significantly compared with other approaches.
1 December 2015 in Journal of Computing and Information Technology
Radio frequency identification (RFID) has spread into many fields. Its security and privacy has received more and more attention. Based on traditional authentication protocols, some other branches related to practical applications have been introduced including server-less authentication and searching protocols. The server-less searching protocol is extended from server-less authentication protocol and both of them are executedwithout the support from the backend servers. Through analyzing some proposed protocols, we found that the probabilistic tracking attack is one of the major threats on the serverless RFID security protocols. The probability of being tracked and the cost on computation are related with the probability of the undesired tag’s response. Based on the analysis, a practical conclusion is given which can be used in most of the server-less RFID systems.