No abstract

No abstract

In response to the surging challenge in the number and types of mobile malware targeting smart devices and their sophistication in malicious behavior camouflage, we propose to compose a traffic behavior modeling method based on one-dimensional convolutional neural network with autoencoder and independent recurrent neural network (1DCAE-IndRNN) for mobile malware detection. The design solves the problem that most existing approaches for mobile malware traffic detection struggle with capturing the network traffic dynamics and the sequential characteristics of anomalies in the traffic. We reconstruct and apply the one-dimensional convolutional neural network to extract local features from multiple network flows. The autoencoder is applied to digest the principal traffic features from the neural network and is integrated into the independent recurrent neural network construction to highlight the sequential relationship between the highly significant features. In addition, the Softmax function with the LReLU activation function is adjusted and embedded to the neurons of the independent recurrent neural network to effectively alleviate the problem of unstable training. We conduct a series of experiments to evaluate the effectiveness of the proposed method and its performance for the 1DCAE-IndRNN-integrated detection procedure. The detection results of the public Android malware dataset CICAndMal2017 show that the proposed method achieves up to 98% detection accuracy and recall rates with clear advantages over other benchmark methods.

No abstract

Cloud storage is one of the most widely-used storage services, because it can provide users with unlimited, scalable, low-cost and convenient resource services. When data is outsourced to cloud for storage, data security and access control are the two essential issues that need to be addressed. Attribute-based encryption (ABE) scheme can provide sufficient data security and fine-grained access control for cloud data. As more and more attention is drawn to privacy protection, privacy preservation becomes another urgent issue for cloud storage. In ABE, since the access policies are generally stored in clear text, it will lead to the disclosure of users’ privacy. Some works sacrifice computational efficiency, key length or ciphertext size for privacy concerns. To solve these problems, this paper proposes an efficient privacy-preserving attribute-based encryption scheme with hidden policy for outsourced data. Using the idea of Boolean equivalent transformation, the proposed scheme achieves fast encryption and privacy protection for both data owner and legitimate visitors. In addition, the proposed scheme can satisfy constant secret key length and reasonable size of ciphertext requirements. We also conduct theoretical security analysis, and carry out experiments to prove that the proposed scheme has good performance in terms of computation, communication and storage overheads.