With the rapid development of cloud storage technology, cloud data assured deletion has received extensive attention. While ensuring the deletion of cloud data, users have also placed increasing demands on cloud data assured deletion, such as improving the execution efficiency of various stages of a cloud data assured deletion system and performing fine-grained access and deletion operations. In this paper, we propose an efficient scheme of cloud data assured deletion. The scheme replaces complicated bilinear pairing with simple scalar multiplication on elliptic curves to realize ciphertext policy attribute-based encryption of cloud data, while solving the security problem of shared data. In addition, the efficiency of encryption and decryption is improved, and fine-grained access of ciphertext is realized. The scheme designs an attribute key management system that employs a dual-server to solve system flaws caused by single point failure. The scheme is proven to be secure, based on the decisional Diffie-Hellman assumption in the standard model; therefore, it has stronger security. The theoretical analysis and experimental results show that the scheme guarantees security and significantly improves the efficiency of each stage of cloud data assured deletion.
Lots of machine learning tasks require dealing with graph data, and among them, scene graph generation is a challenging one that calls for graph neural networks’ potential ability. In this paper, we present a definition of graph neural network (GNN) consists of node, edge and global attribute, as well as their corresponding update and aggregate functions. Based on this, we then propose a realization of GNN model called Graph-LSTM and use it in scene graph generation. The model first extracts the item features in the image as the initial states of the node-LSTM representing subject/object and edge-LSTM representing predicate. Two LSTMs update the states via LSTM’s timestep and aggregate information via message passing. Repeat the update-aggregate until convergence. Meanwhile, the tag feature, i.e., the generated probability distribution of image’s semantic concepts is sent to the LSTM through a semantic compositional network (SCN). The SCN-LSTM is trained in an ensemble style, and hence allows the tag feature to serve as the global attribute providing context information to all individuals. The LSTMs’ final states are input to inference modules and generate the triplet (subject, predicate, object) of the scene graph. Experimental results show that Graph-LSTM outperforms the Message Passing and the attention Graph Covolutional Network methods, proving the effectiveness of the proposed scheme.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.