Summary The number of malware has exploded due to the openness of the Android platform, and the endless stream of malware poses a threat to the privacy, tariffs, and device of mobile phone users. A novel Android mobile malware detection system is proposed, which employs an optimized deep convolutional neural network to learn from opcode sequences. The optimized convolutional neural network is trained multiple times by the raw opcode sequences extracted from the decompiled Android file, so that the feature information can be effectively learned and the malicious program can be detected more accurately. More critically, the k‐max pooling method with better results is adopted in the pooling operation phase, which improves the detection effect of the proposed method. The experimental results show that the detection system achieved the accuracy of 99%, which is 2%‐11% higher than the accuracy of the machine learning detection algorithms when using the same data set. It also ensures that the indicators, such as F1‐score, recall, and precision, are maintained above 97%. Based on the detection system, a multi–data set comparison experiment is carried out. The introduced k‐max pooling is deeply studied, and the effect of k of k‐max pooling on the overall detection effect is observed.

No abstract

Summary Wearable devices, which provide the services of collecting personal data, monitoring health conditions, and so on, are widely used in many fields, ranging from sports to healthcare. Although wearable devices bring convenience to people's lives, they bring about significant security concerns, such as personal privacy disclosure and unauthorized access to wearable devices. To ensure the privacy and security of the sensitive data, it is critical to design an efficient authentication protocol suitable for wearable devices. Recently, Das et al proposed a lightweight authentication protocol, which achieves secure communication between the wearable device and the mobile terminal. However, we find that their protocol is vulnerable to offline password guessing attack and desynchronization attack. Therefore, we put forward a user centric three‐factor authentication scheme for wearable devices assisted by cloud server. Informal security analysis and formal analysis using ProVerif is executed to demonstrate that our protocol not only remedies the flaws of the protocol of Das et al but also meets desired security properties. Comparison with related schemes shows that our protocol satisfies security and usability simultaneously.

No abstract

Unlike the traditional medical system, telecare medicine information system (TMIS) ensures that patients can get health-care services via the Internet at home. Authenticated key agreement protocol is very important for protecting the security in TMIS. Recently scholars have proposed a lot of authenticated key agreement protocols. In 2016, Chiou et al. demonstrated that Chen et al.'s authentication scheme fails to provide user's anonymity and message authentication and then proposed an enhanced scheme (Chiou et al., J. Med. Syst. 40(4):1-15, 2006) to overcome these drawbacks. In this paper, we demonstrate that Chiou et al.'s scheme is defenseless against key compromise impersonation (KCI) attack and also fails to provide forward security. Moreover, we propose a novel authentication scheme namely ICASME to overcome the mentioned weaknesses in this paper. Security analyses show that ICASME achieves the forward security and KCI attack resistance. In addition, it is proved that the time taken to implement the ICASME is not intolerable compared to the original protocol.